[GH-ISSUE #13549] Regression: Vision models (MiniCPM-V, llava:7b) stop processing images starting in Ollama 0.13.3 #55438

New Issue

Open

opened 2026-04-29 09:12:13 -05:00 by GiteaMirror · 5 comments

GiteaMirror commented 2026-04-29 09:12:13 -05:00

Owner

Copy Link

Originally created by @blackeagle0001 on GitHub (Dec 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13549

What is the issue?

Error Description:

Vision models correctly process image inputs in Ollama 0.13.1 and 0.13.2, but break starting with Ollama 0.13.3 under identical conditions.

• Vision and non-vision models load successfully
• Text-only prompts continue to work
• When an image is provided, the image input is either ignored or leads to runner instability
• Vision preprocessing (vision encoder load and image slicing) still executes
• Failure occurs later during inference, in some cases causing the runner to crash with a sampler assertion:
  llama-sampling.cpp:660: Assertion `found' failed
• Downgrading to 0.13.2 immediately restores full vision functionality
• Regression window is clearly identified: 0.13.2 (working) → 0.13.3+ (broken)

This behavior is reproducible across multiple vision models and is not related to hardware, drivers, CUDA, models, prompts, or workflows.

Environment:

• Debian Linux (systemd) 6.12.30+bpo-amd64 1 SMP PREEMPT_DYNAMIC Debian 6.12.30-1~bpo12+1 (2025-06-14) x86_64 GNU/Linux
• NVIDIA RTX 2060 (6 GB), Driver Version: 535.247.01
• CUDA backend, CUDA Version: 12.2
• Official install script, via curl -fsSL https://ollama.com/install.sh

Same hardware, drivers, models, prompts, and workflows across tests

Minimal reproduction:

• ollama run minicpm-v "Describe this image" --image test.jpg

Related issues (possibly connected, but not duplicates):

• #13506 – sampler assertion failure
• #13537 – vision models produce no output when images are provided

This issue differs in that it identifies a clear regression window: vision models work in 0.13.2 and fail starting in 0.13.3 under identical conditions.

Workaround:

Pin Ollama to 0.13.2.

Relevant log output

Ollama 0.13.5 (broken):

Repeated runner restarts when an image is provided:
msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine -port 43821"
msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine -port 36545"

Occasional GPU discovery timeout during runner startup:
error="failed to finish discovery before timeout" path="/usr/local/lib/ollama/cuda_v12"

Vision preprocessing still executes (vision encoder load + image slicing):
clip_model_loader: has vision encoder
get_slice_instructions: slice 0: x=0, y=0, size=490x406

Fatal crash during sampling:
ollama: llama-sampling.cpp:660: void llama_sampler_dist_apply(llama_sampler*, llama_token_data_array*): Assertion 
`found' failed.
SIGABRT

Request fails after runner crash:
time=2025-12-22T21:12:00.372-06:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:35755/completion\": EOF"

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.13.3 to 0.13.5

Originally created by @blackeagle0001 on GitHub (Dec 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13549 ### What is the issue? ### Error Description: Vision models correctly process image inputs in Ollama 0.13.1 and 0.13.2, but break starting with Ollama 0.13.3 under identical conditions. - Vision and non-vision models load successfully - Text-only prompts continue to work - When an image is provided, the image input is either ignored or leads to runner instability - Vision preprocessing (vision encoder load and image slicing) still executes - Failure occurs later during inference, in some cases causing the runner to crash with a sampler assertion: llama-sampling.cpp:660: Assertion `found' failed - Downgrading to 0.13.2 immediately restores full vision functionality - Regression window is clearly identified: 0.13.2 (working) → 0.13.3+ (broken) This behavior is reproducible across multiple vision models and is not related to hardware, drivers, CUDA, models, prompts, or workflows. ### Environment: - Debian Linux (systemd) 6.12.30+bpo-amd64 1 SMP PREEMPT_DYNAMIC Debian 6.12.30-1~bpo12+1 (2025-06-14) x86_64 GNU/Linux - NVIDIA RTX 2060 (6 GB), Driver Version: 535.247.01 - CUDA backend, CUDA Version: 12.2 - Official install script, via curl -fsSL https://ollama.com/install.sh Same hardware, drivers, models, prompts, and workflows across tests ### Minimal reproduction: - ollama run minicpm-v "Describe this image" --image test.jpg ### Related issues (possibly connected, but not duplicates): - #13506 – sampler assertion failure - #13537 – vision models produce no output when images are provided This issue differs in that it identifies a clear regression window: vision models work in 0.13.2 and fail starting in 0.13.3 under identical conditions. ### Workaround: Pin Ollama to 0.13.2. ### Relevant log output ```shell Ollama 0.13.5 (broken): Repeated runner restarts when an image is provided: msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine -port 43821" msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine -port 36545" Occasional GPU discovery timeout during runner startup: error="failed to finish discovery before timeout" path="/usr/local/lib/ollama/cuda_v12" Vision preprocessing still executes (vision encoder load + image slicing): clip_model_loader: has vision encoder get_slice_instructions: slice 0: x=0, y=0, size=490x406 Fatal crash during sampling: ollama: llama-sampling.cpp:660: void llama_sampler_dist_apply(llama_sampler*, llama_token_data_array*): Assertion `found' failed. SIGABRT Request fails after runner crash: time=2025-12-22T21:12:00.372-06:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:35755/completion\": EOF" ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.13.3 to 0.13.5

GiteaMirror added the bug label 2026-04-29 09:12:13 -05:00

GiteaMirror commented 2026-04-29 09:12:15 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Dec 23, 2025):

Provide a full log.

$ ollama -v
ollama version is 0.13.5
$ ollama run minicpm-v describe this image ./image1.png 
Added image './image1.png'
A small white puppy with a red collar and gold bell sits on the pavement, attentively looking off to its 
right. The background is blurred but appears to be an outdoor setting. There's nothing else in sight that 
could indicate a specific context or story beyond the casual moment captured of the young dog observing 
something out of frame.

<!-- gh-comment-id:3685184108 --> @rick-github commented on GitHub (Dec 23, 2025): Provide a full log. ```console $ ollama -v ollama version is 0.13.5 $ ollama run minicpm-v describe this image ./image1.png Added image './image1.png' A small white puppy with a red collar and gold bell sits on the pavement, attentively looking off to its right. The background is blurred but appears to be an outdoor setting. There's nothing else in sight that could indicate a specific context or story beyond the casual moment captured of the young dog observing something out of frame. ```

GiteaMirror commented 2026-04-29 09:12:15 -05:00

Author

Owner

Copy Link

@blackeagle0001 commented on GitHub (Dec 24, 2025):

$ ollama --version
ollama version is 0.13.5

$ ollama run minicpm-v describe this image /tmp/penguin.png
Added image '/tmp/penguin.png'
Error: 500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details

Dec 23 23:44:18 llm-ai ollama[759534]: [GIN] 2025/12/23 - 23:44:18 | 200 | 30.936µs | 127.0.0.1 | HEAD "/"
Dec 23 23:44:18 llm-ai ollama[759534]: [GIN] 2025/12/23 - 23:44:18 | 200 | 66.652409ms | 127.0.0.1 | POST "/api/show"
Dec 23 23:44:18 llm-ai ollama[759534]: time=2025-12-23T23:44:18.901-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 35547"
Dec 23 23:44:19 llm-ai ollama[759534]: time=2025-12-23T23:44:19.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42993"
Dec 23 23:44:19 llm-ai ollama[759534]: time=2025-12-23T23:44:19.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 35855"
Dec 23 23:44:19 llm-ai ollama[759534]: time=2025-12-23T23:44:19.758-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42863"
Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42649"
Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41541"
Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42967"
Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.759-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33725"
Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41107"
Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38973"
Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42253"
Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.758-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38481"
Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45431"
Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37823"
Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43579"
Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.759-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33817"
Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33435"
Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46395"
Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 36089"
Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.758-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44085"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37647"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.009-06:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.009-06:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.009-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32917"
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest))
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 0: general.architecture str = qwen2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 1: general.name str = model
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 10: general.file_type u32 = 2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", """, "#", "$", "%", "&", "'", ...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 21: general.quantization_version u32 = 2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type f32: 141 tensors
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q4_0: 197 tensors
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q6_K: 1 tensors
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file format = GGUF V3 (latest)
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file type = Q4_0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file size = 4.12 GiB (4.65 BPW)
Dec 23 23:44:24 llm-ai ollama[759534]: load: printing all EOG tokens:
Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151643 ('<|endoftext|>')
Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151645 ('<|im_end|>')
Dec 23 23:44:24 llm-ai ollama[759534]: load: special tokens cache size = 25
Dec 23 23:44:24 llm-ai ollama[759534]: load: token to piece cache size = 0.9309 MB
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: arch = qwen2
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab_only = 1
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: no_alloc = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model type = ?B
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model params = 7.61 B
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: general.name = model
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab type = BPE
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_vocab = 151666
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_merges = 151387
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: BOS token = 151644 '<|im_start|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOS token = 151645 '<|im_end|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOT token = 151645 '<|im_end|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: UNK token = 128244 ''
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: PAD token = 0 '!'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: LF token = 198 'Ċ'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151643 '<|endoftext|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151645 '<|im_end|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: max token length = 256
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_load: vocab only - skipping tensors
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 --port 33931"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=sched.go:443 msg="system memory" total="15.6 GiB" free="14.1 GiB" free_swap="840.2 MiB"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed library=CUDA available="5.3 GiB" free="5.8 GiB" minimum="457.0 MiB" overhead="0 B"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=server.go:496 msg="loading model" "model layers"=29 requested=-1
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.8 GiB"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="224.0 MiB"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="303.2 MiB"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:272 msg="total memory" size="4.3 GiB"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.541-06:00 level=INFO source=runner.go:965 msg="starting go runner"
Dec 23 23:44:24 llm-ai ollama[759534]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so
Dec 23 23:44:24 llm-ai ollama[759534]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
Dec 23 23:44:24 llm-ai ollama[759534]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Dec 23 23:44:24 llm-ai ollama[759534]: ggml_cuda_init: found 1 CUDA devices:
Dec 23 23:44:24 llm-ai ollama[759534]: Device 0: NVIDIA GeForce RTX 2060, compute capability 7.5, VMM: yes, ID: GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed
Dec 23 23:44:24 llm-ai ollama[759534]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.608-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.609-06:00 level=INFO source=runner.go:1001 msg="Server listening on 127.0.0.1:33931"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.613-06:00 level=INFO source=runner.go:895 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Auto KvSize:4096 KvCacheType: NumThreads:4 GPULayers:29[ID:GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed Layers:29(0..28)] MultiUserCache:false ProjectorPath:/mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0 MainGPU:0 UseMmap:true}"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.613-06:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding"
Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.614-06:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model"
Dec 23 23:44:24 llm-ai ollama[759534]: ggml_backend_cuda_device_get_memory device GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed utilizing NVML memory reporting free: 6210453504 total: 6442450944
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2060) (0000:01:00.0) - 5922 MiB free
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest))
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 0: general.architecture str = qwen2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 1: general.name str = model
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 10: general.file_type u32 = 2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", """, "#", "$", "%", "&", "'", ...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo...
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 21: general.quantization_version u32 = 2
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type f32: 141 tensors
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q4_0: 197 tensors
Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q6_K: 1 tensors
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file format = GGUF V3 (latest)
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file type = Q4_0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file size = 4.12 GiB (4.65 BPW)
Dec 23 23:44:24 llm-ai ollama[759534]: load: printing all EOG tokens:
Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151643 ('<|endoftext|>')
Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151645 ('<|im_end|>')
Dec 23 23:44:24 llm-ai ollama[759534]: load: special tokens cache size = 25
Dec 23 23:44:24 llm-ai ollama[759534]: load: token to piece cache size = 0.9309 MB
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: arch = qwen2
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab_only = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: no_alloc = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_ctx_train = 32768
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd = 3584
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_inp = 3584
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_layer = 28
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_head = 28
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_head_kv = 4
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_rot = 128
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_swa = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: is_swa_any = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_head_k = 128
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_head_v = 128
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_gqa = 7
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_k_gqa = 512
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_v_gqa = 512
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_norm_eps = 0.0e+00
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_norm_rms_eps = 1.0e-06
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_clamp_kqv = 0.0e+00
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_max_alibi_bias = 0.0e+00
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_logit_scale = 0.0e+00
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_attn_scale = 0.0e+00
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_ff = 18944
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_expert = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_expert_used = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_expert_groups = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_group_used = 0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: causal attn = 1
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: pooling type = -1
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope type = 2
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope scaling = linear
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: freq_base_train = 1000000.0
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: freq_scale_train = 1
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_ctx_orig_yarn = 32768
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope_yarn_log_mul= 0.0000
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope_finetuned = unknown
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model type = 7B
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model params = 7.61 B
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: general.name = model
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab type = BPE
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_vocab = 151666
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_merges = 151387
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: BOS token = 151644 '<|im_start|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOS token = 151645 '<|im_end|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOT token = 151645 '<|im_end|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: UNK token = 128244 ''
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: PAD token = 0 '!'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: LF token = 198 'Ċ'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151643 '<|endoftext|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151645 '<|im_end|>'
Dec 23 23:44:24 llm-ai ollama[759534]: print_info: max token length = 256
Dec 23 23:44:24 llm-ai ollama[759534]: load_tensors: loading model tensors, this can take a while... (mmap = true)
Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: offloading 28 repeating layers to GPU
Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: offloading output layer to GPU
Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: offloaded 29/29 layers to GPU
Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: CPU_Mapped model buffer size = 291.59 MiB
Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: CUDA0 model buffer size = 3926.95 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: constructing llama_context
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_seq_max = 1
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ctx = 4096
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ctx_seq = 4096
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_batch = 512
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ubatch = 512
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: causal_attn = 1
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: flash_attn = auto
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: kv_unified = false
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: freq_base = 1000000.0
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: freq_scale = 1
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ctx_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: CUDA_Host output buffer size = 0.59 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: llama_kv_cache: CUDA0 KV buffer size = 224.00 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: llama_kv_cache: size = 224.00 MiB ( 4096 cells, 28 layers, 1/1 seqs), K (f16): 112.00 MiB, V (f16): 112.00 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: Flash Attention was auto, set to enabled
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: CUDA0 compute buffer size = 303.22 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: CUDA_Host compute buffer size = 15.01 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: graph nodes = 959
Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: graph splits = 2
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: model name:
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: description: image encoder for MiniCPM-V
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: GGUF version: 3
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: alignment: 32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: n_tensors: 455
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: n_kv: 19
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: has vision encoder
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=917504, offset=0, shape:[3584, 64, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=70246400, offset=917504, shape:[3584, 4900, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=25690112, offset=71163904, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=8257536, offset=96854016, shape:[1152, 3584, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=25690112, offset=105111552, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=25690112, offset=130801664, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=25690112, offset=156491776, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=14336, offset=182181888, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=14336, offset=182196224, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=14336, offset=182210560, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=25690112, offset=182224896, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=14336, offset=207915008, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=14336, offset=207929344, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=14336, offset=207943680, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=14336, offset=207958016, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=14336, offset=207972352, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=14336, offset=207986688, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=14336, offset=208001024, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=208015360, shape:[14, 14, 3, 1152], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=209370112, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=209374720, shape:[1152, 4900, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=220664320, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=223318528, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=223323136, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=225977344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=225981952, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=228636160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=228640768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=231294976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=231299584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=231304192, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=231308800, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=241225216, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=241242432, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=251158848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=251163456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=251168064, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=251172672, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=253826880, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=253831488, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=256485696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=256490304, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=259144512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=259149120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=261803328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=261807936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=261812544, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=261817152, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=271733568, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=271750784, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=281667200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=281671808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=281676416, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=281681024, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=284335232, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=284339840, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=286994048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=286998656, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=289652864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=289657472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=292311680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=292316288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=292320896, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=292325504, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=302241920, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=302259136, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=312175552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=312180160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=312184768, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=312189376, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=314843584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=314848192, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=317502400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=317507008, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=320161216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=320165824, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=322820032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=322824640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=322829248, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=322833856, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=332750272, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=332767488, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=342683904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=342688512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=342693120, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=342697728, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=345351936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=345356544, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=348010752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=348015360, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=350669568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=350674176, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=353328384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=353332992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=353337600, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=353342208, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=363258624, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=363275840, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=373192256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=373196864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=373201472, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=373206080, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=375860288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=375864896, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=378519104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=378523712, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=381177920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=381182528, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=383836736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=383841344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=383845952, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=383850560, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=393766976, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=393784192, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=403700608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=403705216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=403709824, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=403714432, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=406368640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=406373248, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=409027456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=409032064, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=411686272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=411690880, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=414345088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=414349696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=414354304, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=414358912, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=424275328, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=424292544, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=434208960, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=434213568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=434218176, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=434222784, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=436876992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=436881600, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=439535808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=439540416, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=442194624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=442199232, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=444853440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=444858048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=444862656, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=444867264, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=454783680, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=454800896, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=464717312, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=464721920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=464726528, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=464731136, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=467385344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=467389952, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=470044160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=470048768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=472702976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=472707584, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=475361792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=475366400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=475371008, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=475375616, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=485292032, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=485309248, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=495225664, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=495230272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=495234880, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=495239488, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=497893696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=497898304, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=500552512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=500557120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=503211328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=503215936, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=505870144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=505874752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=505879360, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=505883968, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=515800384, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=515817600, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=525734016, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=525738624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=525743232, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=525747840, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=528402048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=528406656, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=531060864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=531065472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=533719680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=533724288, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=536378496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=536383104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=536387712, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=536392320, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=546308736, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=546325952, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=556242368, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=556246976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=556251584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=556256192, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=558910400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=558915008, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=561569216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=561573824, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=564228032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=564232640, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=566886848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=566891456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=566896064, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=566900672, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=576817088, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=576834304, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=586750720, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=586755328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=586759936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=586764544, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=589418752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=589423360, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=592077568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=592082176, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=594736384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=594740992, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=597395200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=597399808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=597404416, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=597409024, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=607325440, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=607342656, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=617259072, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=617263680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=617268288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=617272896, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=619927104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=619931712, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=622585920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=622590528, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=625244736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=625249344, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=627903552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=627908160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=627912768, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=627917376, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=637833792, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=637851008, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=647767424, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=647772032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=647776640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=647781248, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=650435456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=650440064, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=653094272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=653098880, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=655753088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=655757696, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=658411904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=658416512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=658421120, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=658425728, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=668342144, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=668359360, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=678275776, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=678280384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=678284992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=678289600, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=680943808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=680948416, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=683602624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=683607232, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=686261440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=686266048, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=688920256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=688924864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=688929472, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=688934080, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=698850496, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=698867712, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=708784128, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=708788736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=708793344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=708797952, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=711452160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=711456768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=714110976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=714115584, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=716769792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=716774400, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=719428608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=719433216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=719437824, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=719442432, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=729358848, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=729376064, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=739292480, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=739297088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=739301696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=739306304, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=741960512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=741965120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=744619328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=744623936, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=747278144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=747282752, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=749936960, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=749941568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=749946176, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=749950784, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=759867200, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=759884416, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=769800832, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=769805440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=769810048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=769814656, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=772468864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=772473472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=775127680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=775132288, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=777786496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=777791104, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=780445312, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=780449920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=780454528, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=780459136, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=790375552, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=790392768, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=800309184, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=800313792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=800318400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=800323008, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=802977216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=802981824, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=805636032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=805640640, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=808294848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=808299456, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=810953664, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=810958272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=810962880, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=810967488, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=820883904, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=820901120, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=830817536, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=830822144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=830826752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=830831360, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=833485568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=833490176, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=836144384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=836148992, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=838803200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=838807808, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=841462016, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=841466624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=841471232, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=841475840, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=851392256, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=851409472, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=861325888, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=861330496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=861335104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=861339712, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=863993920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=863998528, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=866652736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=866657344, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=869311552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=869316160, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=871970368, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=871974976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=871979584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=871984192, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=881900608, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=881917824, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=891834240, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=891838848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=891843456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=891848064, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=894502272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=894506880, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=897161088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=897165696, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=899819904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=899824512, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=902478720, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=902483328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=902487936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=902492544, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=912408960, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=912426176, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=922342592, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=922347200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=922351808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=922356416, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=925010624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=925015232, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=927669440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=927674048, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=930328256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=930332864, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=932987072, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=932991680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=932996288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=933000896, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=942917312, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=942934528, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=952850944, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=952855552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=952860160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=952864768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=955518976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=955523584, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=958177792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=958182400, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=960836608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=960841216, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=963495424, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=963500032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=963504640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=963509248, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=973425664, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=973442880, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=983359296, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=983363904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=983368512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=983373120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=986027328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=986031936, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=988686144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=988690752, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=991344960, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=991349568, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=994003776, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=994008384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=994012992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=994017600, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=1003934016, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=1003951232, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=1013867648, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=1013872256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=1013876864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=1013881472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=1016535680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=1016540288, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=1019194496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=1019199104, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=1021853312, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=1021857920, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=1024512128, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=1024516736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=1024521344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=1024525952, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=1034442368, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=1034459584, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=1044376000, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=1044380608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=1044385216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=1044389824, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=1044394432, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:44:26 llm-ai ollama[759534]: clip_ctx: CLIP using CUDA0 backend
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: projector: resampler
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_embd: 1152
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_head: 16
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_ff: 4304
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_layer: 26
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: ffn_op: gelu
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: projection_dim: 0
Dec 23 23:44:26 llm-ai ollama[759534]: --- vision hparams ---
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: image_size: 448
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: patch_size: 14
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: has_llava_proj: 0
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: minicpmv_version: 3
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_merge: 0
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_wa_pattern: 0
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: model size: 996.02 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: metadata size: 0.16 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: load_tensors: ffn up/down are swapped
Dec 23 23:44:26 llm-ai ollama[759534]: load_tensors: loaded 439 tensors from /mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0
Dec 23 23:44:26 llm-ai ollama[759534]: warmup: warmup with image size = 448 x 448
Dec 23 23:44:26 llm-ai ollama[759534]: alloc_compute_meta: CUDA0 compute buffer size = 53.31 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: alloc_compute_meta: CPU compute buffer size = 2.31 MiB
Dec 23 23:44:26 llm-ai ollama[759534]: alloc_compute_meta: graph splits = 1, nodes = 862
Dec 23 23:44:26 llm-ai ollama[759534]: warmup: flash attention is enabled
Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.627-06:00 level=INFO source=server.go:1376 msg="llama runner started in 2.10 seconds"
Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.628-06:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.628-06:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding"
Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.628-06:00 level=INFO source=server.go:1376 msg="llama runner started in 2.10 seconds"
Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: original size: 800 x 629, overview size: 504 x 392, refined size: 1008 x 784, grid size: 2 x 2
Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 0: x=0, y=0, size=504x392
Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 1: x=504, y=0, size=504x392
Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 2: x=0, y=392, size=504x392
Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 3: x=504, y=392, size=504x392
Dec 23 23:44:27 llm-ai ollama[759534]: ollama: llama-sampling.cpp:660: void llama_sampler_dist_apply(llama_sampler*, llama_token_data_array*): Assertion `found' failed.
Dec 23 23:44:27 llm-ai ollama[759534]: SIGABRT: abort
Dec 23 23:44:27 llm-ai ollama[759534]: PC=0x7f3f53ca9eec m=5 sigcode=18446744073709551610
Dec 23 23:44:27 llm-ai ollama[759534]: signal arrived during cgo execution
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 6 gp=0xc000504fc0 m=5 mp=0xc000100008 [syscall]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.cgocall(0x5578a62f0820, 0xc000073c70)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/cgocall.go:167 +0x4b fp=0xc000073c48 sp=0xc000073c10 pc=0x5578a559f6eb
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama._Cfunc_common_sampler_csample(0x7f3dfcd8c9f0, 0x7f3efe756e40, 0x8)
Dec 23 23:44:27 llm-ai ollama[759534]: _cgo_gotypes.go:425 +0x4a fp=0xc000073c70 sp=0xc000073c48 pc=0x5578a59579ca
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch.(*SamplingContext).Sample.func1(...)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama/llama.go:679
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama.(*SamplingContext).Sample(...)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama/llama.go:679
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0000d74a0, 0xc00058c370, 0xc00058c3c0)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:539 +0x69b fp=0xc000073ee8 sp=0xc000073c70 pc=0x5578a5a1381b
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0000d74a0, {0x5578a6b58410, 0xc0000a8dc0})
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:387 +0x1d5 fp=0xc000073fb8 sp=0xc000073ee8 pc=0x5578a5a13015
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x28 fp=0xc000073fe0 sp=0xc000073fb8 pc=0x5578a5a183e8
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x4c5
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 1 gp=0xc000002380 m=nil [IO wait]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc0000f7790 sp=0xc0000f7770 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.netpollblock(0xc00009d7e0?, 0xa553c2a6?, 0x78?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:575 +0xf7 fp=0xc0000f77c8 sp=0xc0000f7790 pc=0x5578a5567e97
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.runtime_pollWait(0x7f3f53a46de0, 0x72)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:351 +0x85 fp=0xc0000f77e8 sp=0xc0000f77c8 pc=0x5578a55a1d85
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).wait(0xc000495080?, 0x900000036?, 0x0)
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000f7810 sp=0xc0000f77e8 pc=0x5578a5629f07
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).waitRead(...)
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:89
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*FD).Accept(0xc000495080)
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_unix.go:620 +0x295 fp=0xc0000f78b8 sp=0xc0000f7810 pc=0x5578a562f2d5
Dec 23 23:44:27 llm-ai ollama[759534]: net.(*netFD).accept(0xc000495080)
Dec 23 23:44:27 llm-ai ollama[759534]: net/fd_unix.go:172 +0x29 fp=0xc0000f7970 sp=0xc0000f78b8 pc=0x5578a56a21a9
Dec 23 23:44:27 llm-ai ollama[759534]: net.(*TCPListener).accept(0xc00043d280)
Dec 23 23:44:27 llm-ai ollama[759534]: net/tcpsock_posix.go:159 +0x1b fp=0xc0000f79c0 sp=0xc0000f7970 pc=0x5578a56b7b5b
Dec 23 23:44:27 llm-ai ollama[759534]: net.(*TCPListener).Accept(0xc00043d280)
Dec 23 23:44:27 llm-ai ollama[759534]: net/tcpsock.go:380 +0x30 fp=0xc0000f79f0 sp=0xc0000f79c0 pc=0x5578a56b6a10
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*onceCloseListener).Accept(0xc0000da3f0?)
Dec 23 23:44:27 llm-ai ollama[759534]: :1 +0x24 fp=0xc0000f7a08 sp=0xc0000f79f0 pc=0x5578a58ce1e4
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*Server).Serve(0xc000037000, {0x5578a6b55dc0, 0xc00043d280})
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3424 +0x30c fp=0xc0000f7b38 sp=0xc0000f7a08 pc=0x5578a58a5aac
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000130140, 0x4, 0x4})
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:1002 +0x8f5 fp=0xc0000f7d08 sp=0xc0000f7b38 pc=0x5578a5a18175
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner.Execute({0xc000130130?, 0x0?, 0x0?})
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc0000f7d30 sp=0xc0000f7d08 pc=0x5578a5ac3cf4
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000036d00?, {0x5578a66380ad?, 0x4?, 0x5578a66380b1?})
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/cmd/cmd.go:1841 +0x45 fp=0xc0000f7d58 sp=0xc0000f7d30 pc=0x5578a6280f25
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).execute(0xc0000dd508, {0xc00043d080, 0x4, 0x4})
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0000f7e78 sp=0xc0000f7d58 pc=0x5578a571b7fc
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0000b8908)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0000f7f30 sp=0xc0000f7e78 pc=0x5578a571c045
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).Execute(...)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:992
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:985
Dec 23 23:44:27 llm-ai ollama[759534]: main.main()
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0000f7f50 sp=0xc0000f7f30 pc=0x5578a6281a0d
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.main()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:283 +0x29d fp=0xc0000f7fe0 sp=0xc0000f7f50 pc=0x5578a556f51d
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000f7fe8 sp=0xc0000f7fe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000060fa8 sp=0xc000060f88 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goparkunlock(...)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:441
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.forcegchelper()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:348 +0xb8 fp=0xc000060fe0 sp=0xc000060fa8 pc=0x5578a556f858
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000060fe8 sp=0xc000060fe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.init.7 in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:336 +0x1a
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000061780 sp=0xc000061760 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goparkunlock(...)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:441
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.bgsweep(0xc00008a000)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgcsweep.go:316 +0xdf fp=0xc0000617c8 sp=0xc000061780 pc=0x5578a5559fff
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcenable.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:204 +0x25 fp=0xc0000617e0 sp=0xc0000617c8 pc=0x5578a554e3e5
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000617e8 sp=0xc0000617e0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcenable in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:204 +0x66
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x10000?, 0x5578a68092a0?, 0x0?, 0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000061f78 sp=0xc000061f58 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goparkunlock(...)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:441
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.(*scavengerState).park(0x5578a742c280)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000061fa8 sp=0xc000061f78 pc=0x5578a5557a49
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.bgscavenge(0xc00008a000)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000061fc8 sp=0xc000061fa8 pc=0x5578a5557fd9
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcenable.gowrap2()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:205 +0x25 fp=0xc000061fe0 sp=0xc000061fc8 pc=0x5578a554e385
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000061fe8 sp=0xc000061fe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcenable in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:205 +0xa5
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x5578a6b42250?, 0x50?, 0x65?, 0x1000000010?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000060630 sp=0xc000060610 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.runfinq()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mfinal.go:196 +0x107 fp=0xc0000607e0 sp=0xc000060630 pc=0x5578a554d3a7
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000607e8 sp=0xc0000607e0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.createfing in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mfinal.go:166 +0x3d
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 19 gp=0xc000103180 m=nil [chan receive]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0xc000229720?, 0xc000546060?, 0x60?, 0xc7?, 0x5578a5688de8?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00005c718 sp=0xc00005c6f8 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.chanrecv(0xc000110310, 0x0, 0x1)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/chan.go:664 +0x445 fp=0xc00005c790 sp=0xc00005c718 pc=0x5578a553ee85
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.chanrecv1(0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/chan.go:506 +0x12 fp=0xc00005c7b8 sp=0xc00005c790 pc=0x5578a553ea12
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1796
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1799 +0x2f fp=0xc00005c7e0 sp=0xc00005c7b8 pc=0x5578a555158f
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00005c7e8 sp=0xc00005c7e0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1794 +0x85
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 20 gp=0xc000103880 m=nil [GC worker (idle)]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00005cf38 sp=0xc00005cf18 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc00005cfc8 sp=0xc00005cf38 pc=0x5578a55508a9
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc00005cfe0 sp=0xc00005cfc8 pc=0x5578a5550785
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00005cfe8 sp=0xc00005cfe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x5578a74fa680?, 0x1?, 0x8f?, 0xf4?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5578a55508a9
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5578a5550785
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x38a5e4d69c174?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000062738 sp=0xc000062718 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc0000627c8 sp=0xc000062738 pc=0x5578a55508a9
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc0000627e0 sp=0xc0000627c8 pc=0x5578a5550785
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000627e8 sp=0xc0000627e0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x38a5e6bb3ed53?, 0x1?, 0x44?, 0xa4?, 0x0?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x5578a55508a9
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1()
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x5578a5550785
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 7 gp=0xc000505180 m=nil [select]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0xc000045a78?, 0x2?, 0xa?, 0x0?, 0xc0000458cc?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000045700 sp=0xc0000456e0 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.selectgo(0xc000045a78, 0xc0000458c8, 0x156?, 0x0, 0x1?, 0x1)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/select.go:351 +0x837 fp=0xc000045838 sp=0xc000045700 pc=0x5578a5581a17
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0000d74a0, {0x5578a6b55fa0, 0xc000176620}, 0xc00008a780)
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:716 +0xbe5 fp=0xc000045ac0 sp=0xc000045838 pc=0x5578a5a15385
Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x5578a6b55fa0?, 0xc000176620?}, 0xc000045b40?)
Dec 23 23:44:27 llm-ai ollama[759534]: :1 +0x36 fp=0xc000045af0 sp=0xc000045ac0 pc=0x5578a5a187f6
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.HandlerFunc.ServeHTTP(0xc00009f740?, {0x5578a6b55fa0?, 0xc000176620?}, 0xc000045b60?)
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:2294 +0x29 fp=0xc000045b18 sp=0xc000045af0 pc=0x5578a58a20e9
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*ServeMux).ServeHTTP(0x5578a55478c5?, {0x5578a6b55fa0, 0xc000176620}, 0xc00008a780)
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:2822 +0x1c4 fp=0xc000045b68 sp=0xc000045b18 pc=0x5578a58a3fe4
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.serverHandler.ServeHTTP({0x5578a6b52590?}, {0x5578a6b55fa0?, 0xc000176620?}, 0x1?)
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3301 +0x8e fp=0xc000045b98 sp=0xc000045b68 pc=0x5578a58c1a6e
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*conn).serve(0xc0000da3f0, {0x5578a6b583d8, 0xc00058b1a0})
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:2102 +0x625 fp=0xc000045fb8 sp=0xc000045b98 pc=0x5578a58a05e5
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*Server).Serve.gowrap3()
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3454 +0x28 fp=0xc000045fe0 sp=0xc000045fb8 pc=0x5578a58a5ea8
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000045fe8 sp=0xc000045fe0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by net/http.(*Server).Serve in goroutine 1
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3454 +0x485
Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 27 gp=0xc0005056c0 m=nil [IO wait]:
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00050b5d8 sp=0xc00050b5b8 pc=0x5578a55a2b6e
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.netpollblock(0x5578a55c6338?, 0xa553c2a6?, 0x78?)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:575 +0xf7 fp=0xc00050b610 sp=0xc00050b5d8 pc=0x5578a5567e97
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.runtime_pollWait(0x7f3f53a46cc8, 0x72)
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:351 +0x85 fp=0xc00050b630 sp=0xc00050b610 pc=0x5578a55a1d85
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).wait(0xc000495100?, 0xc00058b2a1?, 0x0)
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00050b658 sp=0xc00050b630 pc=0x5578a5629f07
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).waitRead(...)
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:89
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*FD).Read(0xc000495100, {0xc00058b2a1, 0x1, 0x1})
Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_unix.go:165 +0x27a fp=0xc00050b6f0 sp=0xc00050b658 pc=0x5578a562b1fa
Dec 23 23:44:27 llm-ai ollama[759534]: net.(*netFD).Read(0xc000495100, {0xc00058b2a1?, 0xc00043d358?, 0xc00050b770?})
Dec 23 23:44:27 llm-ai ollama[759534]: net/fd_posix.go:55 +0x25 fp=0xc00050b738 sp=0xc00050b6f0 pc=0x5578a56a0205
Dec 23 23:44:27 llm-ai ollama[759534]: net.(*conn).Read(0xc00011c920, {0xc00058b2a1?, 0x0?, 0x0?})
Dec 23 23:44:27 llm-ai ollama[759534]: net/net.go:194 +0x45 fp=0xc00050b780 sp=0xc00050b738 pc=0x5578a56ae5c5
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*connReader).backgroundRead(0xc00058b290)
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:690 +0x37 fp=0xc00050b7c8 sp=0xc00050b780 pc=0x5578a589a4b7
Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*connReader).startBackgroundRead.gowrap2()
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:686 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x5578a589a3e5
Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({})
Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x5578a55aaa01
Dec 23 23:44:27 llm-ai ollama[759534]: created by net/http.(*connReader).startBackgroundRead in goroutine 7
Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:686 +0xb6
Dec 23 23:44:27 llm-ai ollama[759534]: rax 0x0
Dec 23 23:44:27 llm-ai ollama[759534]: rbx 0xba090
Dec 23 23:44:27 llm-ai ollama[759534]: rcx 0x7f3f53ca9eec
Dec 23 23:44:27 llm-ai ollama[759534]: rdx 0x6
Dec 23 23:44:27 llm-ai ollama[759534]: rdi 0xba08c
Dec 23 23:44:27 llm-ai ollama[759534]: rsi 0xba090
Dec 23 23:44:27 llm-ai ollama[759534]: rbp 0x7f3f0b8fc6c0
Dec 23 23:44:27 llm-ai ollama[759534]: rsp 0x7f3f0b8fbb80
Dec 23 23:44:27 llm-ai ollama[759534]: r8 0x7
Dec 23 23:44:27 llm-ai ollama[759534]: r9 0x7f3e02f17550
Dec 23 23:44:27 llm-ai ollama[759534]: r10 0x8
Dec 23 23:44:27 llm-ai ollama[759534]: r11 0x246
Dec 23 23:44:27 llm-ai ollama[759534]: r12 0x6
Dec 23 23:44:27 llm-ai ollama[759534]: r13 0x294
Dec 23 23:44:27 llm-ai ollama[759534]: r14 0x5578a6845407
Dec 23 23:44:27 llm-ai ollama[759534]: r15 0x7f3dfcd8cb90
Dec 23 23:44:27 llm-ai ollama[759534]: rip 0x7f3f53ca9eec
Dec 23 23:44:27 llm-ai ollama[759534]: rflags 0x246
Dec 23 23:44:27 llm-ai ollama[759534]: cs 0x33
Dec 23 23:44:27 llm-ai ollama[759534]: fs 0x0
Dec 23 23:44:27 llm-ai ollama[759534]: gs 0x0
Dec 23 23:44:27 llm-ai ollama[759534]: time=2025-12-23T23:44:27.843-06:00 level=ERROR source=server.go:1583 msg="post predict" error="Post "http://127.0.0.1:33931/completion": EOF"
Dec 23 23:44:27 llm-ai ollama[759534]: [GIN] 2025/12/23 - 23:44:27 | 500 | 9.073554424s | 127.0.0.1 | POST "/api/generate"

This is the image used for testing from https://openclipart.org/detail/170053/little-penguin, original size: 800 x 629 px:

<!-- gh-comment-id:3688756576 --> @blackeagle0001 commented on GitHub (Dec 24, 2025): $ ollama --version ollama version is 0.13.5 $ ollama run minicpm-v describe this image /tmp/penguin.png Added image '/tmp/penguin.png' Error: 500 Internal Server Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details Dec 23 23:44:18 llm-ai ollama[759534]: [GIN] 2025/12/23 - 23:44:18 | 200 | 30.936µs | 127.0.0.1 | HEAD "/" Dec 23 23:44:18 llm-ai ollama[759534]: [GIN] 2025/12/23 - 23:44:18 | 200 | 66.652409ms | 127.0.0.1 | POST "/api/show" Dec 23 23:44:18 llm-ai ollama[759534]: time=2025-12-23T23:44:18.901-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 35547" Dec 23 23:44:19 llm-ai ollama[759534]: time=2025-12-23T23:44:19.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42993" Dec 23 23:44:19 llm-ai ollama[759534]: time=2025-12-23T23:44:19.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 35855" Dec 23 23:44:19 llm-ai ollama[759534]: time=2025-12-23T23:44:19.758-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42863" Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42649" Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41541" Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42967" Dec 23 23:44:20 llm-ai ollama[759534]: time=2025-12-23T23:44:20.759-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33725" Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41107" Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38973" Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42253" Dec 23 23:44:21 llm-ai ollama[759534]: time=2025-12-23T23:44:21.758-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38481" Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45431" Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37823" Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43579" Dec 23 23:44:22 llm-ai ollama[759534]: time=2025-12-23T23:44:22.759-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33817" Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33435" Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.258-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46395" Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.508-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 36089" Dec 23 23:44:23 llm-ai ollama[759534]: time=2025-12-23T23:44:23.758-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44085" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.008-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37647" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.009-06:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[] error="failed to finish discovery before timeout" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.009-06:00 level=WARN source=runner.go:356 msg="unable to refresh free memory, using old values" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.009-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32917" Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest)) Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 0: general.architecture str = qwen2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 1: general.name str = model Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 10: general.file_type u32 = 2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", "\"", "#", "$", "%", "&", "'", ... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 21: general.quantization_version u32 = 2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type f32: 141 tensors Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q4_0: 197 tensors Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q6_K: 1 tensors Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file format = GGUF V3 (latest) Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file type = Q4_0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file size = 4.12 GiB (4.65 BPW) Dec 23 23:44:24 llm-ai ollama[759534]: load: printing all EOG tokens: Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151643 ('<|endoftext|>') Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151645 ('<|im_end|>') Dec 23 23:44:24 llm-ai ollama[759534]: load: special tokens cache size = 25 Dec 23 23:44:24 llm-ai ollama[759534]: load: token to piece cache size = 0.9309 MB Dec 23 23:44:24 llm-ai ollama[759534]: print_info: arch = qwen2 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab_only = 1 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: no_alloc = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model type = ?B Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model params = 7.61 B Dec 23 23:44:24 llm-ai ollama[759534]: print_info: general.name = model Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab type = BPE Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_vocab = 151666 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_merges = 151387 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: BOS token = 151644 '<|im_start|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOS token = 151645 '<|im_end|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOT token = 151645 '<|im_end|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: UNK token = 128244 '<unk>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: PAD token = 0 '!' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: LF token = 198 'Ċ' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151643 '<|endoftext|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151645 '<|im_end|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: max token length = 256 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_load: vocab only - skipping tensors Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 --port 33931" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=sched.go:443 msg="system memory" total="15.6 GiB" free="14.1 GiB" free_swap="840.2 MiB" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed library=CUDA available="5.3 GiB" free="5.8 GiB" minimum="457.0 MiB" overhead="0 B" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.525-06:00 level=INFO source=server.go:496 msg="loading model" "model layers"=29 requested=-1 Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.8 GiB" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="224.0 MiB" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="303.2 MiB" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.526-06:00 level=INFO source=device.go:272 msg="total memory" size="4.3 GiB" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.541-06:00 level=INFO source=runner.go:965 msg="starting go runner" Dec 23 23:44:24 llm-ai ollama[759534]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so Dec 23 23:44:24 llm-ai ollama[759534]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Dec 23 23:44:24 llm-ai ollama[759534]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Dec 23 23:44:24 llm-ai ollama[759534]: ggml_cuda_init: found 1 CUDA devices: Dec 23 23:44:24 llm-ai ollama[759534]: Device 0: NVIDIA GeForce RTX 2060, compute capability 7.5, VMM: yes, ID: GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed Dec 23 23:44:24 llm-ai ollama[759534]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.608-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.609-06:00 level=INFO source=runner.go:1001 msg="Server listening on 127.0.0.1:33931" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.613-06:00 level=INFO source=runner.go:895 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Auto KvSize:4096 KvCacheType: NumThreads:4 GPULayers:29[ID:GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed Layers:29(0..28)] MultiUserCache:false ProjectorPath:/mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0 MainGPU:0 UseMmap:true}" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.613-06:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" Dec 23 23:44:24 llm-ai ollama[759534]: time=2025-12-23T23:44:24.614-06:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model" Dec 23 23:44:24 llm-ai ollama[759534]: ggml_backend_cuda_device_get_memory device GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed utilizing NVML memory reporting free: 6210453504 total: 6442450944 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2060) (0000:01:00.0) - 5922 MiB free Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest)) Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 0: general.architecture str = qwen2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 1: general.name str = model Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 10: general.file_type u32 = 2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", "\"", "#", "$", "%", "&", "'", ... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo... Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - kv 21: general.quantization_version u32 = 2 Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type f32: 141 tensors Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q4_0: 197 tensors Dec 23 23:44:24 llm-ai ollama[759534]: llama_model_loader: - type q6_K: 1 tensors Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file format = GGUF V3 (latest) Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file type = Q4_0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: file size = 4.12 GiB (4.65 BPW) Dec 23 23:44:24 llm-ai ollama[759534]: load: printing all EOG tokens: Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151643 ('<|endoftext|>') Dec 23 23:44:24 llm-ai ollama[759534]: load: - 151645 ('<|im_end|>') Dec 23 23:44:24 llm-ai ollama[759534]: load: special tokens cache size = 25 Dec 23 23:44:24 llm-ai ollama[759534]: load: token to piece cache size = 0.9309 MB Dec 23 23:44:24 llm-ai ollama[759534]: print_info: arch = qwen2 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab_only = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: no_alloc = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_ctx_train = 32768 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd = 3584 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_inp = 3584 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_layer = 28 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_head = 28 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_head_kv = 4 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_rot = 128 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_swa = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: is_swa_any = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_head_k = 128 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_head_v = 128 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_gqa = 7 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_k_gqa = 512 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_embd_v_gqa = 512 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_norm_eps = 0.0e+00 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_norm_rms_eps = 1.0e-06 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_clamp_kqv = 0.0e+00 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_max_alibi_bias = 0.0e+00 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_logit_scale = 0.0e+00 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: f_attn_scale = 0.0e+00 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_ff = 18944 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_expert = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_expert_used = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_expert_groups = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_group_used = 0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: causal attn = 1 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: pooling type = -1 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope type = 2 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope scaling = linear Dec 23 23:44:24 llm-ai ollama[759534]: print_info: freq_base_train = 1000000.0 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: freq_scale_train = 1 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_ctx_orig_yarn = 32768 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope_yarn_log_mul= 0.0000 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: rope_finetuned = unknown Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model type = 7B Dec 23 23:44:24 llm-ai ollama[759534]: print_info: model params = 7.61 B Dec 23 23:44:24 llm-ai ollama[759534]: print_info: general.name = model Dec 23 23:44:24 llm-ai ollama[759534]: print_info: vocab type = BPE Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_vocab = 151666 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: n_merges = 151387 Dec 23 23:44:24 llm-ai ollama[759534]: print_info: BOS token = 151644 '<|im_start|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOS token = 151645 '<|im_end|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOT token = 151645 '<|im_end|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: UNK token = 128244 '<unk>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: PAD token = 0 '!' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: LF token = 198 'Ċ' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151643 '<|endoftext|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: EOG token = 151645 '<|im_end|>' Dec 23 23:44:24 llm-ai ollama[759534]: print_info: max token length = 256 Dec 23 23:44:24 llm-ai ollama[759534]: load_tensors: loading model tensors, this can take a while... (mmap = true) Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: offloading 28 repeating layers to GPU Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: offloading output layer to GPU Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: offloaded 29/29 layers to GPU Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: CPU_Mapped model buffer size = 291.59 MiB Dec 23 23:44:25 llm-ai ollama[759534]: load_tensors: CUDA0 model buffer size = 3926.95 MiB Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: constructing llama_context Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_seq_max = 1 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ctx = 4096 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ctx_seq = 4096 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_batch = 512 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ubatch = 512 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: causal_attn = 1 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: flash_attn = auto Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: kv_unified = false Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: freq_base = 1000000.0 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: freq_scale = 1 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: n_ctx_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: CUDA_Host output buffer size = 0.59 MiB Dec 23 23:44:26 llm-ai ollama[759534]: llama_kv_cache: CUDA0 KV buffer size = 224.00 MiB Dec 23 23:44:26 llm-ai ollama[759534]: llama_kv_cache: size = 224.00 MiB ( 4096 cells, 28 layers, 1/1 seqs), K (f16): 112.00 MiB, V (f16): 112.00 MiB Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: Flash Attention was auto, set to enabled Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: CUDA0 compute buffer size = 303.22 MiB Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: CUDA_Host compute buffer size = 15.01 MiB Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: graph nodes = 959 Dec 23 23:44:26 llm-ai ollama[759534]: llama_context: graph splits = 2 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: model name: Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: description: image encoder for MiniCPM-V Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: GGUF version: 3 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: alignment: 32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: n_tensors: 455 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: n_kv: 19 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: has vision encoder Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=917504, offset=0, shape:[3584, 64, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=70246400, offset=917504, shape:[3584, 4900, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=25690112, offset=71163904, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=8257536, offset=96854016, shape:[1152, 3584, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=25690112, offset=105111552, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=25690112, offset=130801664, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=25690112, offset=156491776, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=14336, offset=182181888, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=14336, offset=182196224, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=14336, offset=182210560, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=25690112, offset=182224896, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=14336, offset=207915008, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=14336, offset=207929344, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=14336, offset=207943680, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=14336, offset=207958016, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=14336, offset=207972352, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=14336, offset=207986688, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=14336, offset=208001024, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=208015360, shape:[14, 14, 3, 1152], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=209370112, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=209374720, shape:[1152, 4900, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=220664320, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=223318528, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=223323136, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=225977344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=225981952, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=228636160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=228640768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=231294976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=231299584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=231304192, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=231308800, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=241225216, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=241242432, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=251158848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=251163456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=251168064, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=251172672, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=253826880, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=253831488, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=256485696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=256490304, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=259144512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=259149120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=261803328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=261807936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=261812544, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=261817152, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=271733568, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=271750784, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=281667200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=281671808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=281676416, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=281681024, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=284335232, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=284339840, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=286994048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=286998656, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=289652864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=289657472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=292311680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=292316288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=292320896, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=292325504, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=302241920, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=302259136, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=312175552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=312180160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=312184768, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=312189376, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=314843584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=314848192, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=317502400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=317507008, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=320161216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=320165824, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=322820032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=322824640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=322829248, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=322833856, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=332750272, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=332767488, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=342683904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=342688512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=342693120, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=342697728, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=345351936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=345356544, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=348010752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=348015360, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=350669568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=350674176, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=353328384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=353332992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=353337600, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=353342208, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=363258624, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=363275840, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=373192256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=373196864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=373201472, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=373206080, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=375860288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=375864896, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=378519104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=378523712, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=381177920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=381182528, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=383836736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=383841344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=383845952, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=383850560, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=393766976, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=393784192, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=403700608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=403705216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=403709824, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=403714432, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=406368640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=406373248, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=409027456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=409032064, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=411686272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=411690880, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=414345088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=414349696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=414354304, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=414358912, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=424275328, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=424292544, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=434208960, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=434213568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=434218176, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=434222784, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=436876992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=436881600, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=439535808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=439540416, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=442194624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=442199232, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=444853440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=444858048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=444862656, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=444867264, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=454783680, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=454800896, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=464717312, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=464721920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=464726528, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=464731136, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=467385344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=467389952, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=470044160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=470048768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=472702976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=472707584, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=475361792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=475366400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=475371008, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=475375616, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=485292032, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=485309248, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=495225664, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=495230272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=495234880, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=495239488, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=497893696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=497898304, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=500552512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=500557120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=503211328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=503215936, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=505870144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=505874752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=505879360, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=505883968, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=515800384, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=515817600, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=525734016, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=525738624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=525743232, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=525747840, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=528402048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=528406656, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=531060864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=531065472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=533719680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=533724288, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=536378496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=536383104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=536387712, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=536392320, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=546308736, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=546325952, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=556242368, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=556246976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=556251584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=556256192, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=558910400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=558915008, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=561569216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=561573824, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=564228032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=564232640, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=566886848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=566891456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=566896064, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=566900672, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=576817088, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=576834304, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=586750720, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=586755328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=586759936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=586764544, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=589418752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=589423360, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=592077568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=592082176, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=594736384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=594740992, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=597395200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=597399808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=597404416, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=597409024, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=607325440, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=607342656, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=617259072, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=617263680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=617268288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=617272896, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=619927104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=619931712, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=622585920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=622590528, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=625244736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=625249344, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=627903552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=627908160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=627912768, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=627917376, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=637833792, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=637851008, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=647767424, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=647772032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=647776640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=647781248, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=650435456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=650440064, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=653094272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=653098880, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=655753088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=655757696, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=658411904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=658416512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=658421120, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=658425728, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=668342144, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=668359360, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=678275776, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=678280384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=678284992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=678289600, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=680943808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=680948416, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=683602624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=683607232, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=686261440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=686266048, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=688920256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=688924864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=688929472, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=688934080, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=698850496, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=698867712, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=708784128, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=708788736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=708793344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=708797952, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=711452160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=711456768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=714110976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=714115584, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=716769792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=716774400, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=719428608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=719433216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=719437824, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=719442432, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=729358848, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=729376064, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=739292480, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=739297088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=739301696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=739306304, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=741960512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=741965120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=744619328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=744623936, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=747278144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=747282752, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=749936960, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=749941568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=749946176, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=749950784, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=759867200, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=759884416, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=769800832, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=769805440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=769810048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=769814656, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=772468864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=772473472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=775127680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=775132288, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=777786496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=777791104, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=780445312, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=780449920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=780454528, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=780459136, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=790375552, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=790392768, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=800309184, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=800313792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=800318400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=800323008, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=802977216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=802981824, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=805636032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=805640640, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=808294848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=808299456, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=810953664, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=810958272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=810962880, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=810967488, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=820883904, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=820901120, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=830817536, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=830822144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=830826752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=830831360, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=833485568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=833490176, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=836144384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=836148992, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=838803200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=838807808, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=841462016, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=841466624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=841471232, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=841475840, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=851392256, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=851409472, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=861325888, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=861330496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=861335104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=861339712, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=863993920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=863998528, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=866652736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=866657344, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=869311552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=869316160, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=871970368, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=871974976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=871979584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=871984192, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=881900608, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=881917824, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=891834240, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=891838848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=891843456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=891848064, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=894502272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=894506880, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=897161088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=897165696, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=899819904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=899824512, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=902478720, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=902483328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=902487936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=902492544, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=912408960, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=912426176, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=922342592, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=922347200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=922351808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=922356416, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=925010624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=925015232, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=927669440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=927674048, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=930328256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=930332864, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=932987072, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=932991680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=932996288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=933000896, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=942917312, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=942934528, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=952850944, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=952855552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=952860160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=952864768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=955518976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=955523584, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=958177792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=958182400, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=960836608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=960841216, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=963495424, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=963500032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=963504640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=963509248, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=973425664, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=973442880, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=983359296, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=983363904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=983368512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=983373120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=986027328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=986031936, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=988686144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=988690752, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=991344960, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=991349568, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=994003776, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=994008384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=994012992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=994017600, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=1003934016, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=1003951232, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=1013867648, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=1013872256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=1013876864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=1013881472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=1016535680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=1016540288, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=1019194496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=1019199104, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=1021853312, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=1021857920, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=1024512128, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=1024516736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=1024521344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=1024525952, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=1034442368, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=1034459584, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=1044376000, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=1044380608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=1044385216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=1044389824, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=1044394432, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:44:26 llm-ai ollama[759534]: clip_ctx: CLIP using CUDA0 backend Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: projector: resampler Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_embd: 1152 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_head: 16 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_ff: 4304 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_layer: 26 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: ffn_op: gelu Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: projection_dim: 0 Dec 23 23:44:26 llm-ai ollama[759534]: --- vision hparams --- Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: image_size: 448 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: patch_size: 14 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: has_llava_proj: 0 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: minicpmv_version: 3 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_merge: 0 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: n_wa_pattern: 0 Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: model size: 996.02 MiB Dec 23 23:44:26 llm-ai ollama[759534]: load_hparams: metadata size: 0.16 MiB Dec 23 23:44:26 llm-ai ollama[759534]: load_tensors: ffn up/down are swapped Dec 23 23:44:26 llm-ai ollama[759534]: load_tensors: loaded 439 tensors from /mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0 Dec 23 23:44:26 llm-ai ollama[759534]: warmup: warmup with image size = 448 x 448 Dec 23 23:44:26 llm-ai ollama[759534]: alloc_compute_meta: CUDA0 compute buffer size = 53.31 MiB Dec 23 23:44:26 llm-ai ollama[759534]: alloc_compute_meta: CPU compute buffer size = 2.31 MiB Dec 23 23:44:26 llm-ai ollama[759534]: alloc_compute_meta: graph splits = 1, nodes = 862 Dec 23 23:44:26 llm-ai ollama[759534]: warmup: flash attention is enabled Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.627-06:00 level=INFO source=server.go:1376 msg="llama runner started in 2.10 seconds" Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.628-06:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.628-06:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" Dec 23 23:44:26 llm-ai ollama[759534]: time=2025-12-23T23:44:26.628-06:00 level=INFO source=server.go:1376 msg="llama runner started in 2.10 seconds" Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: original size: 800 x 629, overview size: 504 x 392, refined size: 1008 x 784, grid size: 2 x 2 Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 0: x=0, y=0, size=504x392 Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 1: x=504, y=0, size=504x392 Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 2: x=0, y=392, size=504x392 Dec 23 23:44:26 llm-ai ollama[759534]: get_slice_instructions: slice 3: x=504, y=392, size=504x392 Dec 23 23:44:27 llm-ai ollama[759534]: ollama: llama-sampling.cpp:660: void llama_sampler_dist_apply(llama_sampler*, llama_token_data_array*): Assertion `found' failed. Dec 23 23:44:27 llm-ai ollama[759534]: SIGABRT: abort Dec 23 23:44:27 llm-ai ollama[759534]: PC=0x7f3f53ca9eec m=5 sigcode=18446744073709551610 Dec 23 23:44:27 llm-ai ollama[759534]: signal arrived during cgo execution Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 6 gp=0xc000504fc0 m=5 mp=0xc000100008 [syscall]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.cgocall(0x5578a62f0820, 0xc000073c70) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/cgocall.go:167 +0x4b fp=0xc000073c48 sp=0xc000073c10 pc=0x5578a559f6eb Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama._Cfunc_common_sampler_csample(0x7f3dfcd8c9f0, 0x7f3efe756e40, 0x8) Dec 23 23:44:27 llm-ai ollama[759534]: _cgo_gotypes.go:425 +0x4a fp=0xc000073c70 sp=0xc000073c48 pc=0x5578a59579ca Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch.(*SamplingContext).Sample.func1(...) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama/llama.go:679 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama.(*SamplingContext).Sample(...) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/llama/llama.go:679 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0000d74a0, 0xc00058c370, 0xc00058c3c0) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:539 +0x69b fp=0xc000073ee8 sp=0xc000073c70 pc=0x5578a5a1381b Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0000d74a0, {0x5578a6b58410, 0xc0000a8dc0}) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:387 +0x1d5 fp=0xc000073fb8 sp=0xc000073ee8 pc=0x5578a5a13015 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x28 fp=0xc000073fe0 sp=0xc000073fb8 pc=0x5578a5a183e8 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x4c5 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 1 gp=0xc000002380 m=nil [IO wait]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc0000f7790 sp=0xc0000f7770 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.netpollblock(0xc00009d7e0?, 0xa553c2a6?, 0x78?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:575 +0xf7 fp=0xc0000f77c8 sp=0xc0000f7790 pc=0x5578a5567e97 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.runtime_pollWait(0x7f3f53a46de0, 0x72) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:351 +0x85 fp=0xc0000f77e8 sp=0xc0000f77c8 pc=0x5578a55a1d85 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).wait(0xc000495080?, 0x900000036?, 0x0) Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000f7810 sp=0xc0000f77e8 pc=0x5578a5629f07 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).waitRead(...) Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:89 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*FD).Accept(0xc000495080) Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_unix.go:620 +0x295 fp=0xc0000f78b8 sp=0xc0000f7810 pc=0x5578a562f2d5 Dec 23 23:44:27 llm-ai ollama[759534]: net.(*netFD).accept(0xc000495080) Dec 23 23:44:27 llm-ai ollama[759534]: net/fd_unix.go:172 +0x29 fp=0xc0000f7970 sp=0xc0000f78b8 pc=0x5578a56a21a9 Dec 23 23:44:27 llm-ai ollama[759534]: net.(*TCPListener).accept(0xc00043d280) Dec 23 23:44:27 llm-ai ollama[759534]: net/tcpsock_posix.go:159 +0x1b fp=0xc0000f79c0 sp=0xc0000f7970 pc=0x5578a56b7b5b Dec 23 23:44:27 llm-ai ollama[759534]: net.(*TCPListener).Accept(0xc00043d280) Dec 23 23:44:27 llm-ai ollama[759534]: net/tcpsock.go:380 +0x30 fp=0xc0000f79f0 sp=0xc0000f79c0 pc=0x5578a56b6a10 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*onceCloseListener).Accept(0xc0000da3f0?) Dec 23 23:44:27 llm-ai ollama[759534]: <autogenerated>:1 +0x24 fp=0xc0000f7a08 sp=0xc0000f79f0 pc=0x5578a58ce1e4 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*Server).Serve(0xc000037000, {0x5578a6b55dc0, 0xc00043d280}) Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3424 +0x30c fp=0xc0000f7b38 sp=0xc0000f7a08 pc=0x5578a58a5aac Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000130140, 0x4, 0x4}) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:1002 +0x8f5 fp=0xc0000f7d08 sp=0xc0000f7b38 pc=0x5578a5a18175 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner.Execute({0xc000130130?, 0x0?, 0x0?}) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc0000f7d30 sp=0xc0000f7d08 pc=0x5578a5ac3cf4 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000036d00?, {0x5578a66380ad?, 0x4?, 0x5578a66380b1?}) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/cmd/cmd.go:1841 +0x45 fp=0xc0000f7d58 sp=0xc0000f7d30 pc=0x5578a6280f25 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).execute(0xc0000dd508, {0xc00043d080, 0x4, 0x4}) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc0000f7e78 sp=0xc0000f7d58 pc=0x5578a571b7fc Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0000b8908) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0000f7f30 sp=0xc0000f7e78 pc=0x5578a571c045 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).Execute(...) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:992 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra.(*Command).ExecuteContext(...) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/spf13/cobra@v1.7.0/command.go:985 Dec 23 23:44:27 llm-ai ollama[759534]: main.main() Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0000f7f50 sp=0xc0000f7f30 pc=0x5578a6281a0d Dec 23 23:44:27 llm-ai ollama[759534]: runtime.main() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:283 +0x29d fp=0xc0000f7fe0 sp=0xc0000f7f50 pc=0x5578a556f51d Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000f7fe8 sp=0xc0000f7fe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000060fa8 sp=0xc000060f88 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goparkunlock(...) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:441 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.forcegchelper() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:348 +0xb8 fp=0xc000060fe0 sp=0xc000060fa8 pc=0x5578a556f858 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000060fe8 sp=0xc000060fe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.init.7 in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:336 +0x1a Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000061780 sp=0xc000061760 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goparkunlock(...) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:441 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.bgsweep(0xc00008a000) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgcsweep.go:316 +0xdf fp=0xc0000617c8 sp=0xc000061780 pc=0x5578a5559fff Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcenable.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:204 +0x25 fp=0xc0000617e0 sp=0xc0000617c8 pc=0x5578a554e3e5 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000617e8 sp=0xc0000617e0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcenable in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:204 +0x66 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x10000?, 0x5578a68092a0?, 0x0?, 0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000061f78 sp=0xc000061f58 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goparkunlock(...) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:441 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.(*scavengerState).park(0x5578a742c280) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000061fa8 sp=0xc000061f78 pc=0x5578a5557a49 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.bgscavenge(0xc00008a000) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000061fc8 sp=0xc000061fa8 pc=0x5578a5557fd9 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcenable.gowrap2() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:205 +0x25 fp=0xc000061fe0 sp=0xc000061fc8 pc=0x5578a554e385 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000061fe8 sp=0xc000061fe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcenable in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:205 +0xa5 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x5578a6b42250?, 0x50?, 0x65?, 0x1000000010?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000060630 sp=0xc000060610 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.runfinq() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mfinal.go:196 +0x107 fp=0xc0000607e0 sp=0xc000060630 pc=0x5578a554d3a7 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000607e8 sp=0xc0000607e0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.createfing in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mfinal.go:166 +0x3d Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 19 gp=0xc000103180 m=nil [chan receive]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0xc000229720?, 0xc000546060?, 0x60?, 0xc7?, 0x5578a5688de8?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00005c718 sp=0xc00005c6f8 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.chanrecv(0xc000110310, 0x0, 0x1) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/chan.go:664 +0x445 fp=0xc00005c790 sp=0xc00005c718 pc=0x5578a553ee85 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.chanrecv1(0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/chan.go:506 +0x12 fp=0xc00005c7b8 sp=0xc00005c790 pc=0x5578a553ea12 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1796 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1799 +0x2f fp=0xc00005c7e0 sp=0xc00005c7b8 pc=0x5578a555158f Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00005c7e8 sp=0xc00005c7e0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1794 +0x85 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 20 gp=0xc000103880 m=nil [GC worker (idle)]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00005cf38 sp=0xc00005cf18 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc00005cfc8 sp=0xc00005cf38 pc=0x5578a55508a9 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc00005cfe0 sp=0xc00005cfc8 pc=0x5578a5550785 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00005cfe8 sp=0xc00005cfe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x5578a74fa680?, 0x1?, 0x8f?, 0xf4?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5578a55508a9 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5578a5550785 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x38a5e4d69c174?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000062738 sp=0xc000062718 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc0000627c8 sp=0xc000062738 pc=0x5578a55508a9 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc0000627e0 sp=0xc0000627c8 pc=0x5578a5550785 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000627e8 sp=0xc0000627e0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x38a5e6bb3ed53?, 0x1?, 0x44?, 0xa4?, 0x0?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkWorker(0xc000111730) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x5578a55508a9 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gcBgMarkStartWorkers.gowrap1() Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x5578a5550785 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: runtime/mgc.go:1339 +0x105 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 7 gp=0xc000505180 m=nil [select]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0xc000045a78?, 0x2?, 0xa?, 0x0?, 0xc0000458cc?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc000045700 sp=0xc0000456e0 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.selectgo(0xc000045a78, 0xc0000458c8, 0x156?, 0x0, 0x1?, 0x1) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/select.go:351 +0x837 fp=0xc000045838 sp=0xc000045700 pc=0x5578a5581a17 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0000d74a0, {0x5578a6b55fa0, 0xc000176620}, 0xc00008a780) Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner/runner.go:716 +0xbe5 fp=0xc000045ac0 sp=0xc000045838 pc=0x5578a5a15385 Dec 23 23:44:27 llm-ai ollama[759534]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x5578a6b55fa0?, 0xc000176620?}, 0xc000045b40?) Dec 23 23:44:27 llm-ai ollama[759534]: <autogenerated>:1 +0x36 fp=0xc000045af0 sp=0xc000045ac0 pc=0x5578a5a187f6 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.HandlerFunc.ServeHTTP(0xc00009f740?, {0x5578a6b55fa0?, 0xc000176620?}, 0xc000045b60?) Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:2294 +0x29 fp=0xc000045b18 sp=0xc000045af0 pc=0x5578a58a20e9 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*ServeMux).ServeHTTP(0x5578a55478c5?, {0x5578a6b55fa0, 0xc000176620}, 0xc00008a780) Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:2822 +0x1c4 fp=0xc000045b68 sp=0xc000045b18 pc=0x5578a58a3fe4 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.serverHandler.ServeHTTP({0x5578a6b52590?}, {0x5578a6b55fa0?, 0xc000176620?}, 0x1?) Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3301 +0x8e fp=0xc000045b98 sp=0xc000045b68 pc=0x5578a58c1a6e Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*conn).serve(0xc0000da3f0, {0x5578a6b583d8, 0xc00058b1a0}) Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:2102 +0x625 fp=0xc000045fb8 sp=0xc000045b98 pc=0x5578a58a05e5 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*Server).Serve.gowrap3() Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3454 +0x28 fp=0xc000045fe0 sp=0xc000045fb8 pc=0x5578a58a5ea8 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000045fe8 sp=0xc000045fe0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by net/http.(*Server).Serve in goroutine 1 Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:3454 +0x485 Dec 23 23:44:27 llm-ai ollama[759534]: goroutine 27 gp=0xc0005056c0 m=nil [IO wait]: Dec 23 23:44:27 llm-ai ollama[759534]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/proc.go:435 +0xce fp=0xc00050b5d8 sp=0xc00050b5b8 pc=0x5578a55a2b6e Dec 23 23:44:27 llm-ai ollama[759534]: runtime.netpollblock(0x5578a55c6338?, 0xa553c2a6?, 0x78?) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:575 +0xf7 fp=0xc00050b610 sp=0xc00050b5d8 pc=0x5578a5567e97 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.runtime_pollWait(0x7f3f53a46cc8, 0x72) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/netpoll.go:351 +0x85 fp=0xc00050b630 sp=0xc00050b610 pc=0x5578a55a1d85 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).wait(0xc000495100?, 0xc00058b2a1?, 0x0) Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00050b658 sp=0xc00050b630 pc=0x5578a5629f07 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*pollDesc).waitRead(...) Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_poll_runtime.go:89 Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll.(*FD).Read(0xc000495100, {0xc00058b2a1, 0x1, 0x1}) Dec 23 23:44:27 llm-ai ollama[759534]: internal/poll/fd_unix.go:165 +0x27a fp=0xc00050b6f0 sp=0xc00050b658 pc=0x5578a562b1fa Dec 23 23:44:27 llm-ai ollama[759534]: net.(*netFD).Read(0xc000495100, {0xc00058b2a1?, 0xc00043d358?, 0xc00050b770?}) Dec 23 23:44:27 llm-ai ollama[759534]: net/fd_posix.go:55 +0x25 fp=0xc00050b738 sp=0xc00050b6f0 pc=0x5578a56a0205 Dec 23 23:44:27 llm-ai ollama[759534]: net.(*conn).Read(0xc00011c920, {0xc00058b2a1?, 0x0?, 0x0?}) Dec 23 23:44:27 llm-ai ollama[759534]: net/net.go:194 +0x45 fp=0xc00050b780 sp=0xc00050b738 pc=0x5578a56ae5c5 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*connReader).backgroundRead(0xc00058b290) Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:690 +0x37 fp=0xc00050b7c8 sp=0xc00050b780 pc=0x5578a589a4b7 Dec 23 23:44:27 llm-ai ollama[759534]: net/http.(*connReader).startBackgroundRead.gowrap2() Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:686 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x5578a589a3e5 Dec 23 23:44:27 llm-ai ollama[759534]: runtime.goexit({}) Dec 23 23:44:27 llm-ai ollama[759534]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x5578a55aaa01 Dec 23 23:44:27 llm-ai ollama[759534]: created by net/http.(*connReader).startBackgroundRead in goroutine 7 Dec 23 23:44:27 llm-ai ollama[759534]: net/http/server.go:686 +0xb6 Dec 23 23:44:27 llm-ai ollama[759534]: rax 0x0 Dec 23 23:44:27 llm-ai ollama[759534]: rbx 0xba090 Dec 23 23:44:27 llm-ai ollama[759534]: rcx 0x7f3f53ca9eec Dec 23 23:44:27 llm-ai ollama[759534]: rdx 0x6 Dec 23 23:44:27 llm-ai ollama[759534]: rdi 0xba08c Dec 23 23:44:27 llm-ai ollama[759534]: rsi 0xba090 Dec 23 23:44:27 llm-ai ollama[759534]: rbp 0x7f3f0b8fc6c0 Dec 23 23:44:27 llm-ai ollama[759534]: rsp 0x7f3f0b8fbb80 Dec 23 23:44:27 llm-ai ollama[759534]: r8 0x7 Dec 23 23:44:27 llm-ai ollama[759534]: r9 0x7f3e02f17550 Dec 23 23:44:27 llm-ai ollama[759534]: r10 0x8 Dec 23 23:44:27 llm-ai ollama[759534]: r11 0x246 Dec 23 23:44:27 llm-ai ollama[759534]: r12 0x6 Dec 23 23:44:27 llm-ai ollama[759534]: r13 0x294 Dec 23 23:44:27 llm-ai ollama[759534]: r14 0x5578a6845407 Dec 23 23:44:27 llm-ai ollama[759534]: r15 0x7f3dfcd8cb90 Dec 23 23:44:27 llm-ai ollama[759534]: rip 0x7f3f53ca9eec Dec 23 23:44:27 llm-ai ollama[759534]: rflags 0x246 Dec 23 23:44:27 llm-ai ollama[759534]: cs 0x33 Dec 23 23:44:27 llm-ai ollama[759534]: fs 0x0 Dec 23 23:44:27 llm-ai ollama[759534]: gs 0x0 Dec 23 23:44:27 llm-ai ollama[759534]: time=2025-12-23T23:44:27.843-06:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:33931/completion\": EOF" Dec 23 23:44:27 llm-ai ollama[759534]: [GIN] 2025/12/23 - 23:44:27 | 500 | 9.073554424s | 127.0.0.1 | POST "/api/generate" This is the image used for testing from https://openclipart.org/detail/170053/little-penguin, original size: 800 x 629 px: <img width="266" height="209" alt="Image" src="https://github.com/user-attachments/assets/32196da2-48e0-4599-b9eb-72d4975be0fc" />

GiteaMirror commented 2026-04-29 09:12:16 -05:00

Author

Owner

Copy Link

@blackeagle0001 commented on GitHub (Dec 24, 2025):

And same image no issues with Ollama v. 0.13.2

$ ollama -v
ollama version is 0.13.2

$ ollama run minicpm-v describe this image /tmp/penguin.png
Added image '/tmp/penguin.png'
The image presents a charming depiction of a penguin, rendered in the style of computer graphics. The creature stands upright on two legs and has its arms outstretched to the sides as if welcoming or
balancing itself.

This particular penguin is uniquely dressed for an academic setting. It sports a black graduation cap that sits snugly atop its head, indicating a celebration of education or achievement. Complementing
this scholarly look are orange shoes with silver buckles adorning its feet and hands, adding a pop of color against the predominantly white body.

The background is kept simple and uncluttered to ensure the focus remains on the penguin character. The backdrop consists solely of black space, which contrasts sharply with the figure's bright colors
and solid shape, making it stand out prominently in the image. There are no texts or other objects present in this frame, allowing for a clear and undistracted view of the academic-clad penguin.

In essence, the image captures an amusing blend of wildlife imagery and human cultural symbolism, embodied by the graduation attire on the otherwise innocent-looking penguin character.

Dec 23 23:55:15 llm-ai systemd[1]: Started ollama.service - Ollama Service.
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.708-06:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:1h30m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/mnt/llm-models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.714-06:00 level=INFO source=images.go:522 msg="total blobs: 86"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.716-06:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.717-06:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.2)"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.718-06:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.719-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33991"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.792-06:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.792-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43367"
Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.900-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46825"
Dec 23 23:55:16 llm-ai ollama[762810]: time=2025-12-23T23:55:16.055-06:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed filter_id="" library=CUDA compute=7.5 name=CUDA0 description="NVIDIA GeForce RTX 2060" libdirs=ollama,cuda_v12 driver=12.2 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.8 GiB"
Dec 23 23:55:16 llm-ai ollama[762810]: time=2025-12-23T23:55:16.056-06:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="6.0 GiB" threshold="20.0 GiB"
Dec 23 23:55:18 llm-ai ollama[762810]: [GIN] 2025/12/23 - 23:55:18 | 200 | 56.285µs | 127.0.0.1 | HEAD "/"
Dec 23 23:55:18 llm-ai ollama[762810]: [GIN] 2025/12/23 - 23:55:18 | 200 | 69.472959ms | 127.0.0.1 | POST "/api/show"
Dec 23 23:55:18 llm-ai ollama[762810]: time=2025-12-23T23:55:18.558-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40151"
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest))
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 0: general.architecture str = qwen2
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 1: general.name str = model
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 10: general.file_type u32 = 2
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", """, "#", "$", "%", "&", "'", ...
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo...
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 21: general.quantization_version u32 = 2
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - type f32: 141 tensors
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - type q4_0: 197 tensors
Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - type q6_K: 1 tensors
Dec 23 23:55:18 llm-ai ollama[762810]: print_info: file format = GGUF V3 (latest)
Dec 23 23:55:18 llm-ai ollama[762810]: print_info: file type = Q4_0
Dec 23 23:55:18 llm-ai ollama[762810]: print_info: file size = 4.12 GiB (4.65 BPW)
Dec 23 23:55:19 llm-ai ollama[762810]: load: printing all EOG tokens:
Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151643 ('<|endoftext|>')
Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151645 ('<|im_end|>')
Dec 23 23:55:19 llm-ai ollama[762810]: load: special tokens cache size = 25
Dec 23 23:55:19 llm-ai ollama[762810]: load: token to piece cache size = 0.9309 MB
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: arch = qwen2
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab_only = 1
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model type = ?B
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model params = 7.61 B
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: general.name = model
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab type = BPE
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_vocab = 151666
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_merges = 151387
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: BOS token = 151644 '<|im_start|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOS token = 151645 '<|im_end|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOT token = 151645 '<|im_end|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: UNK token = 128244 ''
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: PAD token = 0 '!'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: LF token = 198 'Ċ'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151643 '<|endoftext|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151645 '<|im_end|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: max token length = 256
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_load: vocab only - skipping tensors
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 --port 44737"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=sched.go:443 msg="system memory" total="15.6 GiB" free="14.2 GiB" free_swap="840.2 MiB"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed library=CUDA available="5.3 GiB" free="5.8 GiB" minimum="457.0 MiB" overhead="0 B"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=server.go:459 msg="loading model" "model layers"=29 requested=-1
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.8 GiB"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="224.0 MiB"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="303.2 MiB"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:272 msg="total memory" size="4.3 GiB"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.094-06:00 level=INFO source=runner.go:963 msg="starting go runner"
Dec 23 23:55:19 llm-ai ollama[762810]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so
Dec 23 23:55:19 llm-ai ollama[762810]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
Dec 23 23:55:19 llm-ai ollama[762810]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Dec 23 23:55:19 llm-ai ollama[762810]: ggml_cuda_init: found 1 CUDA devices:
Dec 23 23:55:19 llm-ai ollama[762810]: Device 0: NVIDIA GeForce RTX 2060, compute capability 7.5, VMM: yes, ID: GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed
Dec 23 23:55:19 llm-ai ollama[762810]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.160-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.161-06:00 level=INFO source=runner.go:999 msg="Server listening on 127.0.0.1:44737"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.167-06:00 level=INFO source=runner.go:893 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:4 GPULayers:29[ID:GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed Layers:29(0..28)] MultiUserCache:false ProjectorPath:/mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0 MainGPU:0 UseMmap:true}"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.168-06:00 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding"
Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.168-06:00 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model"
Dec 23 23:55:19 llm-ai ollama[762810]: ggml_backend_cuda_device_get_memory device GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed utilizing NVML memory reporting free: 6210453504 total: 6442450944
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2060) (0000:01:00.0) - 5922 MiB free
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest))
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 0: general.architecture str = qwen2
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 1: general.name str = model
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 10: general.file_type u32 = 2
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", """, "#", "$", "%", "&", "'", ...
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo...
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 21: general.quantization_version u32 = 2
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - type f32: 141 tensors
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - type q4_0: 197 tensors
Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - type q6_K: 1 tensors
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: file format = GGUF V3 (latest)
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: file type = Q4_0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: file size = 4.12 GiB (4.65 BPW)
Dec 23 23:55:19 llm-ai ollama[762810]: load: printing all EOG tokens:
Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151643 ('<|endoftext|>')
Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151645 ('<|im_end|>')
Dec 23 23:55:19 llm-ai ollama[762810]: load: special tokens cache size = 25
Dec 23 23:55:19 llm-ai ollama[762810]: load: token to piece cache size = 0.9309 MB
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: arch = qwen2
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab_only = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_ctx_train = 32768
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd = 3584
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_inp = 3584
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_layer = 28
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_head = 28
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_head_kv = 4
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_rot = 128
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_swa = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: is_swa_any = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_head_k = 128
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_head_v = 128
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_gqa = 7
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_k_gqa = 512
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_v_gqa = 512
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_norm_eps = 0.0e+00
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_norm_rms_eps = 1.0e-06
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_clamp_kqv = 0.0e+00
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_max_alibi_bias = 0.0e+00
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_logit_scale = 0.0e+00
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_attn_scale = 0.0e+00
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_ff = 18944
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_expert = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_expert_used = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_expert_groups = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_group_used = 0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: causal attn = 1
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: pooling type = -1
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: rope type = 2
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: rope scaling = linear
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: freq_base_train = 1000000.0
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: freq_scale_train = 1
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_ctx_orig_yarn = 32768
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: rope_finetuned = unknown
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model type = 7B
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model params = 7.61 B
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: general.name = model
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab type = BPE
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_vocab = 151666
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_merges = 151387
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: BOS token = 151644 '<|im_start|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOS token = 151645 '<|im_end|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOT token = 151645 '<|im_end|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: UNK token = 128244 ''
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: PAD token = 0 '!'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: LF token = 198 'Ċ'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151643 '<|endoftext|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151645 '<|im_end|>'
Dec 23 23:55:19 llm-ai ollama[762810]: print_info: max token length = 256
Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: loading model tensors, this can take a while... (mmap = true)
Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: offloading 28 repeating layers to GPU
Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: offloading output layer to GPU
Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: offloaded 29/29 layers to GPU
Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: CPU_Mapped model buffer size = 291.59 MiB
Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: CUDA0 model buffer size = 3926.95 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: constructing llama_context
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_seq_max = 1
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ctx = 4096
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ctx_seq = 4096
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_batch = 512
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ubatch = 512
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: causal_attn = 1
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: flash_attn = disabled
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: kv_unified = false
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: freq_base = 1000000.0
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: freq_scale = 1
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ctx_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: CUDA_Host output buffer size = 0.59 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: llama_kv_cache: CUDA0 KV buffer size = 224.00 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: llama_kv_cache: size = 224.00 MiB ( 4096 cells, 28 layers, 1/1 seqs), K (f16): 112.00 MiB, V (f16): 112.00 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: CUDA0 compute buffer size = 303.22 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: CUDA_Host compute buffer size = 17.01 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: graph nodes = 1098
Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: graph splits = 2
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: model name:
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: description: image encoder for MiniCPM-V
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: GGUF version: 3
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: alignment: 32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: n_tensors: 455
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: n_kv: 19
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: has vision encoder
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=917504, offset=0, shape:[3584, 64, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=70246400, offset=917504, shape:[3584, 4900, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=25690112, offset=71163904, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=8257536, offset=96854016, shape:[1152, 3584, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=25690112, offset=105111552, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=25690112, offset=130801664, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=25690112, offset=156491776, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=14336, offset=182181888, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=14336, offset=182196224, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=14336, offset=182210560, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=25690112, offset=182224896, shape:[3584, 3584, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=14336, offset=207915008, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=14336, offset=207929344, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=14336, offset=207943680, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=14336, offset=207958016, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=14336, offset=207972352, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=14336, offset=207986688, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=14336, offset=208001024, shape:[3584, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=208015360, shape:[14, 14, 3, 1152], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=209370112, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=209374720, shape:[1152, 4900, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=220664320, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=223318528, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=223323136, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=225977344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=225981952, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=228636160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=228640768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=231294976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=231299584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=231304192, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=231308800, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=241225216, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=241242432, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=251158848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=251163456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=251168064, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=251172672, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=253826880, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=253831488, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=256485696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=256490304, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=259144512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=259149120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=261803328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=261807936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=261812544, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=261817152, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=271733568, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=271750784, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=281667200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=281671808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=281676416, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=281681024, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=284335232, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=284339840, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=286994048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=286998656, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=289652864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=289657472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=292311680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=292316288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=292320896, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=292325504, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=302241920, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=302259136, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=312175552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=312180160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=312184768, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=312189376, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=314843584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=314848192, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=317502400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=317507008, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=320161216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=320165824, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=322820032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=322824640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=322829248, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=322833856, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=332750272, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=332767488, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=342683904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=342688512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=342693120, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=342697728, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=345351936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=345356544, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=348010752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=348015360, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=350669568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=350674176, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=353328384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=353332992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=353337600, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=353342208, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=363258624, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=363275840, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=373192256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=373196864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=373201472, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=373206080, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=375860288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=375864896, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=378519104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=378523712, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=381177920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=381182528, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=383836736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=383841344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=383845952, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=383850560, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=393766976, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=393784192, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=403700608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=403705216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=403709824, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=403714432, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=406368640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=406373248, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=409027456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=409032064, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=411686272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=411690880, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=414345088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=414349696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=414354304, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=414358912, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=424275328, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=424292544, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=434208960, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=434213568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=434218176, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=434222784, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=436876992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=436881600, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=439535808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=439540416, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=442194624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=442199232, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=444853440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=444858048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=444862656, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=444867264, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=454783680, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=454800896, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=464717312, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=464721920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=464726528, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=464731136, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=467385344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=467389952, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=470044160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=470048768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=472702976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=472707584, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=475361792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=475366400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=475371008, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=475375616, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=485292032, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=485309248, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=495225664, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=495230272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=495234880, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=495239488, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=497893696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=497898304, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=500552512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=500557120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=503211328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=503215936, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=505870144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=505874752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=505879360, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=505883968, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=515800384, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=515817600, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=525734016, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=525738624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=525743232, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=525747840, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=528402048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=528406656, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=531060864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=531065472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=533719680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=533724288, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=536378496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=536383104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=536387712, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=536392320, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=546308736, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=546325952, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=556242368, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=556246976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=556251584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=556256192, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=558910400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=558915008, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=561569216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=561573824, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=564228032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=564232640, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=566886848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=566891456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=566896064, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=566900672, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=576817088, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=576834304, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=586750720, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=586755328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=586759936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=586764544, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=589418752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=589423360, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=592077568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=592082176, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=594736384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=594740992, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=597395200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=597399808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=597404416, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=597409024, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=607325440, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=607342656, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=617259072, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=617263680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=617268288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=617272896, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=619927104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=619931712, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=622585920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=622590528, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=625244736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=625249344, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=627903552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=627908160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=627912768, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=627917376, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=637833792, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=637851008, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=647767424, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=647772032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=647776640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=647781248, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=650435456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=650440064, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=653094272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=653098880, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=655753088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=655757696, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=658411904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=658416512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=658421120, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=658425728, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=668342144, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=668359360, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=678275776, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=678280384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=678284992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=678289600, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=680943808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=680948416, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=683602624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=683607232, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=686261440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=686266048, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=688920256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=688924864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=688929472, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=688934080, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=698850496, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=698867712, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=708784128, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=708788736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=708793344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=708797952, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=711452160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=711456768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=714110976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=714115584, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=716769792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=716774400, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=719428608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=719433216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=719437824, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=719442432, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=729358848, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=729376064, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=739292480, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=739297088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=739301696, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=739306304, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=741960512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=741965120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=744619328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=744623936, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=747278144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=747282752, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=749936960, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=749941568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=749946176, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=749950784, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=759867200, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=759884416, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=769800832, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=769805440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=769810048, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=769814656, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=772468864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=772473472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=775127680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=775132288, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=777786496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=777791104, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=780445312, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=780449920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=780454528, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=780459136, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=790375552, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=790392768, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=800309184, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=800313792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=800318400, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=800323008, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=802977216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=802981824, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=805636032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=805640640, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=808294848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=808299456, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=810953664, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=810958272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=810962880, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=810967488, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=820883904, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=820901120, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=830817536, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=830822144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=830826752, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=830831360, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=833485568, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=833490176, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=836144384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=836148992, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=838803200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=838807808, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=841462016, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=841466624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=841471232, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=841475840, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=851392256, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=851409472, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=861325888, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=861330496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=861335104, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=861339712, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=863993920, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=863998528, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=866652736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=866657344, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=869311552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=869316160, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=871970368, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=871974976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=871979584, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=871984192, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=881900608, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=881917824, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=891834240, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=891838848, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=891843456, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=891848064, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=894502272, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=894506880, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=897161088, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=897165696, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=899819904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=899824512, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=902478720, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=902483328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=902487936, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=902492544, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=912408960, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=912426176, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=922342592, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=922347200, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=922351808, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=922356416, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=925010624, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=925015232, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=927669440, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=927674048, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=930328256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=930332864, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=932987072, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=932991680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=932996288, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=933000896, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=942917312, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=942934528, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=952850944, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=952855552, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=952860160, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=952864768, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=955518976, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=955523584, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=958177792, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=958182400, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=960836608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=960841216, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=963495424, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=963500032, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=963504640, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=963509248, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=973425664, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=973442880, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=983359296, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=983363904, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=983368512, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=983373120, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=986027328, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=986031936, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=988686144, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=988690752, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=991344960, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=991349568, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=994003776, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=994008384, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=994012992, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=994017600, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=1003934016, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=1003951232, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=1013867648, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=1013872256, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=1013876864, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=1013881472, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=1016535680, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=1016540288, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=1019194496, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=1019199104, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=1021853312, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=1021857920, shape:[1152, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=1024512128, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=1024516736, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=1024521344, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=1024525952, shape:[1152, 4304, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=1034442368, shape:[4304, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=1034459584, shape:[4304, 1152, 1, 1], type = f16
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=1044376000, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=1044380608, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=1044385216, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=1044389824, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=1044394432, shape:[1152, 1, 1, 1], type = f32
Dec 23 23:55:20 llm-ai ollama[762810]: clip_ctx: CLIP using CUDA0 backend
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: projector: resampler
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_embd: 1152
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_head: 16
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_ff: 4304
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_layer: 26
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: ffn_op: gelu
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: projection_dim: 0
Dec 23 23:55:20 llm-ai ollama[762810]: --- vision hparams ---
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: image_size: 448
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: patch_size: 14
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: has_llava_proj: 0
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: minicpmv_version: 3
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_merge: 0
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_wa_pattern: 0
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: model size: 996.02 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: metadata size: 0.16 MiB
Dec 23 23:55:20 llm-ai ollama[762810]: load_tensors: ffn up/down are swapped
Dec 23 23:55:21 llm-ai ollama[762810]: load_tensors: loaded 439 tensors from /mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0
Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: warmup with image size = 448 x 448
Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: CUDA0 compute buffer size = 53.31 MiB
Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: CPU compute buffer size = 2.31 MiB
Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: graph splits = 1, nodes = 862
Dec 23 23:55:21 llm-ai ollama[762810]: warmup: flash attention is enabled
Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=server.go:1332 msg="llama runner started in 2.35 seconds"
Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding"
Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=server.go:1332 msg="llama runner started in 2.35 seconds"
Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: original size: 800 x 629, overview size: 504 x 392, refined size: 1008 x 784, grid size: 2 x 2
Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 0: x=0, y=0, size=504x392
Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 1: x=504, y=0, size=504x392
Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 2: x=0, y=392, size=504x392
Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 3: x=504, y=392, size=504x392
Dec 23 23:55:26 llm-ai ollama[762810]: [GIN] 2025/12/23 - 23:55:26 | 200 | 8.340305846s | 127.0.0.1 | POST "/api/generate"

<!-- gh-comment-id:3688771299 --> @blackeagle0001 commented on GitHub (Dec 24, 2025): And same image no issues with Ollama v. 0.13.2 $ ollama -v ollama version is 0.13.2 $ ollama run minicpm-v describe this image /tmp/penguin.png Added image '/tmp/penguin.png' The image presents a charming depiction of a penguin, rendered in the style of computer graphics. The creature stands upright on two legs and has its arms outstretched to the sides as if welcoming or balancing itself. This particular penguin is uniquely dressed for an academic setting. It sports a black graduation cap that sits snugly atop its head, indicating a celebration of education or achievement. Complementing this scholarly look are orange shoes with silver buckles adorning its feet and hands, adding a pop of color against the predominantly white body. The background is kept simple and uncluttered to ensure the focus remains on the penguin character. The backdrop consists solely of black space, which contrasts sharply with the figure's bright colors and solid shape, making it stand out prominently in the image. There are no texts or other objects present in this frame, allowing for a clear and undistracted view of the academic-clad penguin. In essence, the image captures an amusing blend of wildlife imagery and human cultural symbolism, embodied by the graduation attire on the otherwise innocent-looking penguin character. Dec 23 23:55:15 llm-ai systemd[1]: Started ollama.service - Ollama Service. Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.708-06:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:1h30m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/mnt/llm-models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.714-06:00 level=INFO source=images.go:522 msg="total blobs: 86" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.716-06:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.717-06:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.2)" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.718-06:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.719-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33991" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.792-06:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.792-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43367" Dec 23 23:55:15 llm-ai ollama[762810]: time=2025-12-23T23:55:15.900-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46825" Dec 23 23:55:16 llm-ai ollama[762810]: time=2025-12-23T23:55:16.055-06:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed filter_id="" library=CUDA compute=7.5 name=CUDA0 description="NVIDIA GeForce RTX 2060" libdirs=ollama,cuda_v12 driver=12.2 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.8 GiB" Dec 23 23:55:16 llm-ai ollama[762810]: time=2025-12-23T23:55:16.056-06:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="6.0 GiB" threshold="20.0 GiB" Dec 23 23:55:18 llm-ai ollama[762810]: [GIN] 2025/12/23 - 23:55:18 | 200 | 56.285µs | 127.0.0.1 | HEAD "/" Dec 23 23:55:18 llm-ai ollama[762810]: [GIN] 2025/12/23 - 23:55:18 | 200 | 69.472959ms | 127.0.0.1 | POST "/api/show" Dec 23 23:55:18 llm-ai ollama[762810]: time=2025-12-23T23:55:18.558-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40151" Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest)) Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 0: general.architecture str = qwen2 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 1: general.name str = model Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 10: general.file_type u32 = 2 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", "\"", "#", "$", "%", "&", "'", ... Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo... Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - kv 21: general.quantization_version u32 = 2 Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - type f32: 141 tensors Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - type q4_0: 197 tensors Dec 23 23:55:18 llm-ai ollama[762810]: llama_model_loader: - type q6_K: 1 tensors Dec 23 23:55:18 llm-ai ollama[762810]: print_info: file format = GGUF V3 (latest) Dec 23 23:55:18 llm-ai ollama[762810]: print_info: file type = Q4_0 Dec 23 23:55:18 llm-ai ollama[762810]: print_info: file size = 4.12 GiB (4.65 BPW) Dec 23 23:55:19 llm-ai ollama[762810]: load: printing all EOG tokens: Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151643 ('<|endoftext|>') Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151645 ('<|im_end|>') Dec 23 23:55:19 llm-ai ollama[762810]: load: special tokens cache size = 25 Dec 23 23:55:19 llm-ai ollama[762810]: load: token to piece cache size = 0.9309 MB Dec 23 23:55:19 llm-ai ollama[762810]: print_info: arch = qwen2 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab_only = 1 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model type = ?B Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model params = 7.61 B Dec 23 23:55:19 llm-ai ollama[762810]: print_info: general.name = model Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab type = BPE Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_vocab = 151666 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_merges = 151387 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: BOS token = 151644 '<|im_start|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOS token = 151645 '<|im_end|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOT token = 151645 '<|im_end|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: UNK token = 128244 '<unk>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: PAD token = 0 '!' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: LF token = 198 'Ċ' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151643 '<|endoftext|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151645 '<|im_end|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: max token length = 256 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_load: vocab only - skipping tensors Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 --port 44737" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=sched.go:443 msg="system memory" total="15.6 GiB" free="14.2 GiB" free_swap="840.2 MiB" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed library=CUDA available="5.3 GiB" free="5.8 GiB" minimum="457.0 MiB" overhead="0 B" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.078-06:00 level=INFO source=server.go:459 msg="loading model" "model layers"=29 requested=-1 Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="3.8 GiB" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="224.0 MiB" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="303.2 MiB" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.079-06:00 level=INFO source=device.go:272 msg="total memory" size="4.3 GiB" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.094-06:00 level=INFO source=runner.go:963 msg="starting go runner" Dec 23 23:55:19 llm-ai ollama[762810]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so Dec 23 23:55:19 llm-ai ollama[762810]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Dec 23 23:55:19 llm-ai ollama[762810]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Dec 23 23:55:19 llm-ai ollama[762810]: ggml_cuda_init: found 1 CUDA devices: Dec 23 23:55:19 llm-ai ollama[762810]: Device 0: NVIDIA GeForce RTX 2060, compute capability 7.5, VMM: yes, ID: GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed Dec 23 23:55:19 llm-ai ollama[762810]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.160-06:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.161-06:00 level=INFO source=runner.go:999 msg="Server listening on 127.0.0.1:44737" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.167-06:00 level=INFO source=runner.go:893 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:4 GPULayers:29[ID:GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed Layers:29(0..28)] MultiUserCache:false ProjectorPath:/mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0 MainGPU:0 UseMmap:true}" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.168-06:00 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding" Dec 23 23:55:19 llm-ai ollama[762810]: time=2025-12-23T23:55:19.168-06:00 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model" Dec 23 23:55:19 llm-ai ollama[762810]: ggml_backend_cuda_device_get_memory device GPU-b525f9c4-a971-d91d-aa7b-cd89589fe3ed utilizing NVML memory reporting free: 6210453504 total: 6442450944 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2060) (0000:01:00.0) - 5922 MiB free Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: loaded meta data with 22 key-value pairs and 339 tensors from /mnt/llm-models/blobs/sha256-262843d4806aeb402336980badd414a72576b20b1e5d537647da15f16c4a4df0 (version GGUF V3 (latest)) Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 0: general.architecture str = qwen2 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 1: general.name str = model Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 2: qwen2.block_count u32 = 28 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 10: general.file_type u32 = 2 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151666] = ["!", "\"", "#", "$", "%", "&", "'", ... Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151666] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 151644 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 151645 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 128244 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if lo... Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - kv 21: general.quantization_version u32 = 2 Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - type f32: 141 tensors Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - type q4_0: 197 tensors Dec 23 23:55:19 llm-ai ollama[762810]: llama_model_loader: - type q6_K: 1 tensors Dec 23 23:55:19 llm-ai ollama[762810]: print_info: file format = GGUF V3 (latest) Dec 23 23:55:19 llm-ai ollama[762810]: print_info: file type = Q4_0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: file size = 4.12 GiB (4.65 BPW) Dec 23 23:55:19 llm-ai ollama[762810]: load: printing all EOG tokens: Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151643 ('<|endoftext|>') Dec 23 23:55:19 llm-ai ollama[762810]: load: - 151645 ('<|im_end|>') Dec 23 23:55:19 llm-ai ollama[762810]: load: special tokens cache size = 25 Dec 23 23:55:19 llm-ai ollama[762810]: load: token to piece cache size = 0.9309 MB Dec 23 23:55:19 llm-ai ollama[762810]: print_info: arch = qwen2 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab_only = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_ctx_train = 32768 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd = 3584 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_inp = 3584 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_layer = 28 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_head = 28 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_head_kv = 4 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_rot = 128 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_swa = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: is_swa_any = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_head_k = 128 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_head_v = 128 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_gqa = 7 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_k_gqa = 512 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_embd_v_gqa = 512 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_norm_eps = 0.0e+00 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_norm_rms_eps = 1.0e-06 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_clamp_kqv = 0.0e+00 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_max_alibi_bias = 0.0e+00 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_logit_scale = 0.0e+00 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: f_attn_scale = 0.0e+00 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_ff = 18944 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_expert = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_expert_used = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_expert_groups = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_group_used = 0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: causal attn = 1 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: pooling type = -1 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: rope type = 2 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: rope scaling = linear Dec 23 23:55:19 llm-ai ollama[762810]: print_info: freq_base_train = 1000000.0 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: freq_scale_train = 1 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_ctx_orig_yarn = 32768 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: rope_finetuned = unknown Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model type = 7B Dec 23 23:55:19 llm-ai ollama[762810]: print_info: model params = 7.61 B Dec 23 23:55:19 llm-ai ollama[762810]: print_info: general.name = model Dec 23 23:55:19 llm-ai ollama[762810]: print_info: vocab type = BPE Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_vocab = 151666 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: n_merges = 151387 Dec 23 23:55:19 llm-ai ollama[762810]: print_info: BOS token = 151644 '<|im_start|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOS token = 151645 '<|im_end|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOT token = 151645 '<|im_end|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: UNK token = 128244 '<unk>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: PAD token = 0 '!' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: LF token = 198 'Ċ' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151643 '<|endoftext|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: EOG token = 151645 '<|im_end|>' Dec 23 23:55:19 llm-ai ollama[762810]: print_info: max token length = 256 Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: loading model tensors, this can take a while... (mmap = true) Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: offloading 28 repeating layers to GPU Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: offloading output layer to GPU Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: offloaded 29/29 layers to GPU Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: CPU_Mapped model buffer size = 291.59 MiB Dec 23 23:55:19 llm-ai ollama[762810]: load_tensors: CUDA0 model buffer size = 3926.95 MiB Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: constructing llama_context Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_seq_max = 1 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ctx = 4096 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ctx_seq = 4096 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_batch = 512 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ubatch = 512 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: causal_attn = 1 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: flash_attn = disabled Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: kv_unified = false Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: freq_base = 1000000.0 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: freq_scale = 1 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: n_ctx_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: CUDA_Host output buffer size = 0.59 MiB Dec 23 23:55:20 llm-ai ollama[762810]: llama_kv_cache: CUDA0 KV buffer size = 224.00 MiB Dec 23 23:55:20 llm-ai ollama[762810]: llama_kv_cache: size = 224.00 MiB ( 4096 cells, 28 layers, 1/1 seqs), K (f16): 112.00 MiB, V (f16): 112.00 MiB Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: CUDA0 compute buffer size = 303.22 MiB Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: CUDA_Host compute buffer size = 17.01 MiB Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: graph nodes = 1098 Dec 23 23:55:20 llm-ai ollama[762810]: llama_context: graph splits = 2 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: model name: Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: description: image encoder for MiniCPM-V Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: GGUF version: 3 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: alignment: 32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: n_tensors: 455 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: n_kv: 19 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: has vision encoder Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=917504, offset=0, shape:[3584, 64, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=70246400, offset=917504, shape:[3584, 4900, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=25690112, offset=71163904, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=8257536, offset=96854016, shape:[1152, 3584, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=25690112, offset=105111552, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=25690112, offset=130801664, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=25690112, offset=156491776, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=14336, offset=182181888, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=14336, offset=182196224, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=14336, offset=182210560, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=25690112, offset=182224896, shape:[3584, 3584, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=14336, offset=207915008, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=14336, offset=207929344, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=14336, offset=207943680, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=14336, offset=207958016, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=14336, offset=207972352, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=14336, offset=207986688, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=14336, offset=208001024, shape:[3584, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=208015360, shape:[14, 14, 3, 1152], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=209370112, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=209374720, shape:[1152, 4900, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=220664320, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=223318528, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=223323136, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=225977344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=225981952, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=228636160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=228640768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=231294976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=231299584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=231304192, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=231308800, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=241225216, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=241242432, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=251158848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=251163456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=251168064, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=251172672, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=253826880, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=253831488, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=256485696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=256490304, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=259144512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=259149120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=261803328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=261807936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=261812544, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=261817152, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=271733568, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=271750784, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=281667200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=281671808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=281676416, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=281681024, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=284335232, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=284339840, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=286994048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=286998656, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=289652864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=289657472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=292311680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=292316288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=292320896, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=292325504, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=302241920, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=302259136, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=312175552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=312180160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=312184768, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=312189376, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=314843584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=314848192, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=317502400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=317507008, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=320161216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=320165824, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=322820032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=322824640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=322829248, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=322833856, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=332750272, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=332767488, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=342683904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=342688512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=342693120, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=342697728, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=345351936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=345356544, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=348010752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=348015360, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=350669568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=350674176, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=353328384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=353332992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=353337600, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=353342208, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=363258624, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=363275840, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=373192256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=373196864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=373201472, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=373206080, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=375860288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=375864896, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=378519104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=378523712, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=381177920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=381182528, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=383836736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=383841344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=383845952, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=383850560, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=393766976, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=393784192, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=403700608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=403705216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=403709824, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=403714432, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=406368640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=406373248, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=409027456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=409032064, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=411686272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=411690880, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=414345088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=414349696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=414354304, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=414358912, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=424275328, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=424292544, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=434208960, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=434213568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=434218176, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=434222784, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=436876992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=436881600, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=439535808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=439540416, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=442194624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=442199232, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=444853440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=444858048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=444862656, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=444867264, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=454783680, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=454800896, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=464717312, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=464721920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=464726528, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=464731136, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=467385344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=467389952, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=470044160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=470048768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=472702976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=472707584, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=475361792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=475366400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=475371008, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=475375616, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=485292032, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=485309248, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=495225664, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=495230272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=495234880, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=495239488, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=497893696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=497898304, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=500552512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=500557120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=503211328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=503215936, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=505870144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=505874752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=505879360, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=505883968, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=515800384, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=515817600, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=525734016, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=525738624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=525743232, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=525747840, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=528402048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=528406656, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=531060864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=531065472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=533719680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=533724288, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=536378496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=536383104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=536387712, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=536392320, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=546308736, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=546325952, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=556242368, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=556246976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=556251584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=556256192, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=558910400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=558915008, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=561569216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=561573824, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=564228032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=564232640, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=566886848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=566891456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=566896064, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=566900672, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=576817088, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=576834304, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=586750720, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=586755328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=586759936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=586764544, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=589418752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=589423360, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=592077568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=592082176, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=594736384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=594740992, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=597395200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=597399808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=597404416, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=597409024, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=607325440, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=607342656, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=617259072, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=617263680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=617268288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=617272896, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=619927104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=619931712, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=622585920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=622590528, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=625244736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=625249344, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=627903552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=627908160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=627912768, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=627917376, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=637833792, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=637851008, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=647767424, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=647772032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=647776640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=647781248, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=650435456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=650440064, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=653094272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=653098880, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=655753088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=655757696, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=658411904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=658416512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=658421120, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=658425728, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=668342144, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=668359360, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=678275776, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=678280384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=678284992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=678289600, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=680943808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=680948416, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=683602624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=683607232, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=686261440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=686266048, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=688920256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=688924864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=688929472, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=688934080, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=698850496, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=698867712, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=708784128, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=708788736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=708793344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=708797952, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=711452160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=711456768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=714110976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=714115584, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=716769792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=716774400, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=719428608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=719433216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=719437824, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=719442432, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=729358848, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=729376064, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=739292480, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=739297088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=739301696, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=739306304, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=741960512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=741965120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=744619328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=744623936, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=747278144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=747282752, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=749936960, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=749941568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=749946176, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=749950784, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=759867200, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=759884416, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=769800832, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=769805440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=769810048, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=769814656, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=772468864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=772473472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=775127680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=775132288, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=777786496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=777791104, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=780445312, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=780449920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=780454528, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=780459136, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=790375552, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=790392768, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=800309184, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=800313792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=800318400, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=800323008, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=802977216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=802981824, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=805636032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=805640640, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=808294848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=808299456, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=810953664, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=810958272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=810962880, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=810967488, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=820883904, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=820901120, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=830817536, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=830822144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=830826752, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=830831360, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=833485568, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=833490176, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=836144384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=836148992, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=838803200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=838807808, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=841462016, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=841466624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=841471232, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=841475840, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=851392256, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=851409472, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=861325888, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=861330496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=861335104, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=861339712, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=863993920, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=863998528, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=866652736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=866657344, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=869311552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=869316160, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=871970368, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=871974976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=871979584, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=871984192, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=881900608, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=881917824, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=891834240, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=891838848, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=891843456, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=891848064, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=894502272, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=894506880, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=897161088, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=897165696, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=899819904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=899824512, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=902478720, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=902483328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=902487936, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=902492544, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=912408960, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=912426176, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=922342592, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=922347200, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=922351808, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=922356416, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=925010624, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=925015232, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=927669440, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=927674048, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=930328256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=930332864, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=932987072, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=932991680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=932996288, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=933000896, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=942917312, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=942934528, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=952850944, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=952855552, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=952860160, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=952864768, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=955518976, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=955523584, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=958177792, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=958182400, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=960836608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=960841216, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=963495424, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=963500032, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=963504640, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=963509248, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=973425664, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=973442880, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=983359296, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=983363904, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=983368512, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=983373120, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=986027328, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=986031936, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=988686144, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=988690752, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=991344960, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=991349568, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=994003776, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=994008384, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=994012992, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=994017600, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=1003934016, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=1003951232, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=1013867648, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=1013872256, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=1013876864, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=1013881472, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=1016535680, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=1016540288, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=1019194496, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=1019199104, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=1021853312, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=1021857920, shape:[1152, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=1024512128, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=1024516736, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=1024521344, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=1024525952, shape:[1152, 4304, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=1034442368, shape:[4304, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=1034459584, shape:[4304, 1152, 1, 1], type = f16 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=1044376000, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=1044380608, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=1044385216, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=1044389824, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=1044394432, shape:[1152, 1, 1, 1], type = f32 Dec 23 23:55:20 llm-ai ollama[762810]: clip_ctx: CLIP using CUDA0 backend Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: projector: resampler Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_embd: 1152 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_head: 16 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_ff: 4304 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_layer: 26 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: ffn_op: gelu Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: projection_dim: 0 Dec 23 23:55:20 llm-ai ollama[762810]: --- vision hparams --- Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: image_size: 448 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: patch_size: 14 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: has_llava_proj: 0 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: minicpmv_version: 3 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_merge: 0 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: n_wa_pattern: 0 Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: model size: 996.02 MiB Dec 23 23:55:20 llm-ai ollama[762810]: load_hparams: metadata size: 0.16 MiB Dec 23 23:55:20 llm-ai ollama[762810]: load_tensors: ffn up/down are swapped Dec 23 23:55:21 llm-ai ollama[762810]: load_tensors: loaded 439 tensors from /mnt/llm-models/blobs/sha256-f8a805e9e62085805c69c427287acefc284932eb4abfe6e1b1ce431d27e2f4e0 Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: warmup with image size = 448 x 448 Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: CUDA0 compute buffer size = 53.31 MiB Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: CPU compute buffer size = 2.31 MiB Dec 23 23:55:21 llm-ai ollama[762810]: alloc_compute_meta: graph splits = 1, nodes = 862 Dec 23 23:55:21 llm-ai ollama[762810]: warmup: flash attention is enabled Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=server.go:1332 msg="llama runner started in 2.35 seconds" Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding" Dec 23 23:55:21 llm-ai ollama[762810]: time=2025-12-23T23:55:21.428-06:00 level=INFO source=server.go:1332 msg="llama runner started in 2.35 seconds" Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: original size: 800 x 629, overview size: 504 x 392, refined size: 1008 x 784, grid size: 2 x 2 Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 0: x=0, y=0, size=504x392 Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 1: x=504, y=0, size=504x392 Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 2: x=0, y=392, size=504x392 Dec 23 23:55:21 llm-ai ollama[762810]: get_slice_instructions: slice 3: x=504, y=392, size=504x392 Dec 23 23:55:26 llm-ai ollama[762810]: [GIN] 2025/12/23 - 23:55:26 | 200 | 8.340305846s | 127.0.0.1 | POST "/api/generate"

GiteaMirror commented 2026-04-29 09:12:17 -05:00

Author

Owner

Copy Link

@flobernd commented on GitHub (Dec 31, 2025):

I second this issue. The minicpm-v:8b model loads fine and generates chat responses, but as soon as I ask it to analyze an image, I get the exact same error llama-sampling.cpp:660: Assertion 'found' failed.

<!-- gh-comment-id:3702972555 --> @flobernd commented on GitHub (Dec 31, 2025): I second this issue. The `minicpm-v:8b` model loads fine and generates chat responses, but as soon as I ask it to analyze an image, I get the exact same error `llama-sampling.cpp:660: Assertion 'found' failed`.

GiteaMirror commented 2026-04-29 09:12:19 -05:00

Author

Owner

Copy Link

@sinat-jiang commented on GitHub (Jan 8, 2026):

Similar issue, the model I use is Qwen3-VL-Q5-K-M, the gguf format model is from hugging face. The ollama version is 0.13.5, the problem occurred after using the ollama run Qwen3-VL command, the ollama container log is as follows:

time=2026-01-08T02:15:32.540Z level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:42044: runtime error: invalid memory address or nil pointer dereference\ngoroutine 105 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x563f7ff0b2c0?, 0x563f80893410?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel.func1()\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1187 +0x11a\npanic({0x563f7ff0b2c0?, 0x563f80893410?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/ml/nn.(*Conv3D).Forward(0x0, {0x563f80087250, 0xc000fdfe80}, {0x563f80091b20?, 0xc001810018?}, 0x10?, 0xc000180008?, 0xc000ac6000?, 0xc000049190?, 0x0, ...)\n\tgithub.com/ollama/ollama/ml/nn/convolution.go:25 +0x3a\ngithub.com/ollama/ollama/model/models/qwen3vl.(*VisionModel).Forward(0xc0003d60c0, {0x563f80087250, 0xc000fdfe80}, {0x563f80091b20, 0xc001810000}, 0xc000fcc000)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model_vision.go:224 +0x118\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc000d660d0, {0x563f80087250, 0xc000fdfe80}, {0xc001e40000, 0x400436, 0x700000})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:43 +0x14e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0xc0002eb0e0, 0x1)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1098 +0x34e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0002eb0e0, {0x7fff919f4dee?, 0x563f7edbb41a?}, {0x0, 0x30, {0xc000165b00, 0x1, 0x1}, 0x1}, {0x0, ...}, ...)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1226 +0x391\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0002eb0e0, {0x563f80079fa0, 0xc0002e95e0}, 0xc00040fb80)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1305 +0x54b\nnet/http.HandlerFunc.ServeHTTP(0xc0003d6780?, {0x563f80079fa0?, 0xc0002e95e0?}, 0xc0005c9b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x563f7ea6b8c5?, {0x563f80079fa0, 0xc0002e95e0}, 0xc00040fb80)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x563f80076590?}, {0x563f80079fa0?, 0xc0002e95e0?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc00033c6c0, {0x563f8007c3d8, 0xc00045d2f0})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485"
time=2026-01-08T02:15:32.541Z level=INFO source=runner.go:1278 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:Disabled KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-01-08T02:15:32.541Z level=INFO source=sched.go:470 msg="Load failed" model=/root/.ollama/models/blobs/sha256-a4f73cc3dbff6d0706c1b911c2b0c8daa0eb56423a9322322de44b8fdd1f05c1 error="do load request: Post \"http://127.0.0.1:38832/load\": EOF"
time=2026-01-08T02:15:32.585Z level=ERROR source=server.go:302 msg="llama runner terminated" error="signal: killed"

<!-- gh-comment-id:3721632463 --> @sinat-jiang commented on GitHub (Jan 8, 2026): Similar issue, the model I use is `Qwen3-VL-Q5-K-M`, the gguf format model is from hugging face. The ollama version is `0.13.5`, the problem occurred after using the `ollama run Qwen3-VL` command, the ollama container log is as follows: ``` time=2026-01-08T02:15:32.540Z level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:42044: runtime error: invalid memory address or nil pointer dereference\ngoroutine 105 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x563f7ff0b2c0?, 0x563f80893410?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel.func1()\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1187 +0x11a\npanic({0x563f7ff0b2c0?, 0x563f80893410?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/ml/nn.(*Conv3D).Forward(0x0, {0x563f80087250, 0xc000fdfe80}, {0x563f80091b20?, 0xc001810018?}, 0x10?, 0xc000180008?, 0xc000ac6000?, 0xc000049190?, 0x0, ...)\n\tgithub.com/ollama/ollama/ml/nn/convolution.go:25 +0x3a\ngithub.com/ollama/ollama/model/models/qwen3vl.(*VisionModel).Forward(0xc0003d60c0, {0x563f80087250, 0xc000fdfe80}, {0x563f80091b20, 0xc001810000}, 0xc000fcc000)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model_vision.go:224 +0x118\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc000d660d0, {0x563f80087250, 0xc000fdfe80}, {0xc001e40000, 0x400436, 0x700000})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:43 +0x14e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0xc0002eb0e0, 0x1)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1098 +0x34e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc0002eb0e0, {0x7fff919f4dee?, 0x563f7edbb41a?}, {0x0, 0x30, {0xc000165b00, 0x1, 0x1}, 0x1}, {0x0, ...}, ...)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1226 +0x391\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc0002eb0e0, {0x563f80079fa0, 0xc0002e95e0}, 0xc00040fb80)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1305 +0x54b\nnet/http.HandlerFunc.ServeHTTP(0xc0003d6780?, {0x563f80079fa0?, 0xc0002e95e0?}, 0xc0005c9b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x563f7ea6b8c5?, {0x563f80079fa0, 0xc0002e95e0}, 0xc00040fb80)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x563f80076590?}, {0x563f80079fa0?, 0xc0002e95e0?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc00033c6c0, {0x563f8007c3d8, 0xc00045d2f0})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485" time=2026-01-08T02:15:32.541Z level=INFO source=runner.go:1278 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:Disabled KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-01-08T02:15:32.541Z level=INFO source=sched.go:470 msg="Load failed" model=/root/.ollama/models/blobs/sha256-a4f73cc3dbff6d0706c1b911c2b0c8daa0eb56423a9322322de44b8fdd1f05c1 error="do load request: Post \"http://127.0.0.1:38832/load\": EOF" time=2026-01-08T02:15:32.585Z level=ERROR source=server.go:302 msg="llama runner terminated" error="signal: killed" ```

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

v0.23.1

v0.23.1-rc0

v0.23.0

v0.23.0-rc0

v0.22.1

v0.22.1-rc1

v0.22.1-rc0

v0.22.0

v0.22.0-rc1

v0.21.3-rc0

v0.21.2-rc1

v0.21.2

v0.21.2-rc0

v0.21.1

v0.21.1-rc1

v0.21.1-rc0

v0.21.0

v0.21.0-rc1

v0.21.0-rc0

v0.20.8-rc0

v0.20.7

v0.20.7-rc1

v0.20.7-rc0

v0.20.6

v0.20.6-rc1

v0.20.6-rc0

v0.20.5

v0.20.5-rc2

v0.20.5-rc1

v0.20.5-rc0

v0.20.4

v0.20.4-rc2

v0.20.4-rc1

v0.20.4-rc0

v0.20.3

v0.20.3-rc0

v0.20.2

v0.20.1

v0.20.1-rc2

v0.20.1-rc1

v0.20.1-rc0

v0.20.0

v0.20.0-rc1

v0.20.0-rc0

v0.19.0

v0.19.0-rc2

v0.19.0-rc1

v0.19.0-rc0

v0.18.4-rc1

v0.18.4-rc0

v0.18.3

v0.18.3-rc2

v0.18.3-rc1

v0.18.3-rc0

v0.18.2

v0.18.2-rc1

v0.18.2-rc0

v0.18.1

v0.18.1-rc1

v0.18.1-rc0

v0.18.0

v0.18.0-rc2

v0.18.0-rc1

v0.18.0-rc0

v0.17.8-rc4

v0.17.8-rc3

v0.17.8-rc2

v0.17.8-rc1

v0.17.8-rc0

v0.17.7

v0.17.7-rc2

v0.17.7-rc1

v0.17.7-rc0

v0.17.6

v0.17.5

v0.17.4

v0.17.3

v0.17.2

v0.17.1

v0.17.1-rc2

v0.17.1-rc1

v0.17.1-rc0

v0.17.0

v0.17.0-rc2

v0.17.0-rc1

v0.17.0-rc0

v0.16.3

v0.16.3-rc2

v0.16.3-rc1

v0.16.3-rc0

v0.16.2

v0.16.2-rc0

v0.16.1

v0.16.0

v0.16.0-rc2

v0.16.0-rc0

v0.16.0-rc1

v0.15.6

v0.15.5

v0.15.5-rc5

v0.15.5-rc4

v0.15.5-rc3

v0.15.5-rc2

v0.15.5-rc1

v0.15.5-rc0

v0.15.4

v0.15.3

v0.15.2

v0.15.1

v0.15.1-rc1

v0.15.1-rc0

v0.15.0-rc6

v0.15.0

v0.15.0-rc5

v0.15.0-rc4

v0.15.0-rc3

v0.15.0-rc2

v0.15.0-rc1

v0.15.0-rc0

v0.14.3

v0.14.3-rc3

v0.14.3-rc2

v0.14.3-rc1

v0.14.3-rc0

v0.14.2

v0.14.2-rc1

v0.14.2-rc0

v0.14.1

v0.14.0-rc11

v0.14.0

v0.14.0-rc10

v0.14.0-rc9

v0.14.0-rc8

v0.14.0-rc7

v0.14.0-rc6

v0.14.0-rc5

v0.14.0-rc4

v0.14.0-rc3

v0.14.0-rc2

v0.14.0-rc1

v0.14.0-rc0

v0.13.5

v0.13.5-rc1

v0.13.5-rc0

v0.13.4-rc2

v0.13.4

v0.13.4-rc1

v0.13.4-rc0

v0.13.3

v0.13.3-rc1

v0.13.3-rc0

v0.13.2

v0.13.2-rc2

v0.13.2-rc1

v0.13.2-rc0

v0.13.1

v0.13.1-rc2

v0.13.1-rc1

v0.13.1-rc0

v0.13.0

v0.13.0-rc0

v0.12.11

v0.12.11-rc1

v0.12.11-rc0

v0.12.10

v0.12.10-rc1

v0.12.10-rc0

v0.12.9-rc0

v0.12.9

v0.12.8

v0.12.8-rc0

v0.12.7

v0.12.7-rc1

v0.12.7-rc0

v0.12.7-citest0

v0.12.6

v0.12.6-rc1

v0.12.6-rc0

v0.12.5

v0.12.5-rc0

v0.12.4

v0.12.4-rc7

v0.12.4-rc6

v0.12.4-rc5

v0.12.4-rc4

v0.12.4-rc3

v0.12.4-rc2

v0.12.4-rc1

v0.12.4-rc0

v0.12.3

v0.12.2

v0.12.2-rc0

v0.12.1

v0.12.1-rc1

v0.12.1-rc2

v0.12.1-rc0

v0.12.0

v0.12.0-rc1

v0.12.0-rc0

v0.11.11

v0.11.11-rc3

v0.11.11-rc2

v0.11.11-rc1

v0.11.11-rc0

v0.11.10

v0.11.9

v0.11.9-rc0

v0.11.8

v0.11.8-rc0

v0.11.7-rc1

v0.11.7-rc0

v0.11.7

v0.11.6

v0.11.6-rc0

v0.11.5-rc4

v0.11.5-rc3

v0.11.5

v0.11.5-rc5

v0.11.5-rc2

v0.11.5-rc1

v0.11.5-rc0

v0.11.4

v0.11.4-rc0

v0.11.3

v0.11.3-rc0

v0.11.2

v0.11.1

v0.11.0-rc0

v0.11.0-rc1

v0.11.0-rc2

v0.11.0

v0.10.2-int1

v0.10.1

v0.10.0

v0.10.0-rc4

v0.10.0-rc3

v0.10.0-rc2

v0.10.0-rc1

v0.10.0-rc0

v0.9.7-rc1

v0.9.7-rc0

v0.9.6

v0.9.6-rc0

v0.9.6-ci0

v0.9.5

v0.9.4-rc5

v0.9.4-rc6

v0.9.4

v0.9.4-rc3

v0.9.4-rc4

v0.9.4-rc1

v0.9.4-rc2

v0.9.4-rc0

v0.9.3

v0.9.3-rc5

v0.9.4-citest0

v0.9.3-rc4

v0.9.3-rc3

v0.9.3-rc2

v0.9.3-rc1

v0.9.3-rc0

v0.9.2

v0.9.1

v0.9.1-rc1

v0.9.1-rc0

v0.9.1-ci1

v0.9.1-ci0

v0.9.0

v0.9.0-rc0

v0.8.0

v0.8.0-rc0

v0.7.1-rc2

v0.7.1

v0.7.1-rc1

v0.7.1-rc0

v0.7.0

v0.7.0-rc1

v0.7.0-rc0

v0.6.9-rc0

v0.6.8

v0.6.8-rc0

v0.6.7

v0.6.7-rc2

v0.6.7-rc1

v0.6.7-rc0

v0.6.6

v0.6.6-rc2

v0.6.6-rc1

v0.6.6-rc0

v0.6.5-rc1

v0.6.5

v0.6.5-rc0

v0.6.4-rc0

v0.6.4

v0.6.3-rc1

v0.6.3

v0.6.3-rc0

v0.6.2

v0.6.2-rc0

v0.6.1

v0.6.1-rc0

v0.6.0-rc0

v0.6.0

v0.5.14-rc0

v0.5.13

v0.5.13-rc6

v0.5.13-rc5

v0.5.13-rc4

v0.5.13-rc3

v0.5.13-rc2

v0.5.13-rc1

v0.5.13-rc0

v0.5.12

v0.5.12-rc1

v0.5.12-rc0

v0.5.11

v0.5.10

v0.5.9

v0.5.9-rc0

v0.5.8-rc13

v0.5.8

v0.5.8-rc12

v0.5.8-rc11

v0.5.8-rc10

v0.5.8-rc9

v0.5.8-rc8

v0.5.8-rc7

v0.5.8-rc6

v0.5.8-rc5

v0.5.8-rc4

v0.5.8-rc3

v0.5.8-rc2

v0.5.8-rc1

v0.5.8-rc0

v0.5.7

v0.5.6

v0.5.5

v0.5.5-rc0

v0.5.4

v0.5.3

v0.5.3-rc0

v0.5.2

v0.5.2-rc3

v0.5.2-rc2

v0.5.2-rc1

v0.5.2-rc0

v0.5.1

v0.5.0

v0.5.0-rc1

v0.4.8-rc0

v0.4.7

v0.4.6

v0.4.5

v0.4.4

v0.4.3

v0.4.3-rc0

v0.4.2

v0.4.2-rc1

v0.4.2-rc0

v0.4.1

v0.4.1-rc0

v0.4.0

v0.4.0-rc8

v0.4.0-rc7

v0.4.0-rc6

v0.4.0-rc5

v0.4.0-rc4

v0.4.0-rc3

v0.4.0-rc2

v0.4.0-rc1

v0.4.0-rc0

v0.4.0-ci3

v0.3.14

v0.3.14-rc0

v0.3.13

v0.3.12

v0.3.12-rc5

v0.3.12-rc4

v0.3.12-rc3

v0.3.12-rc2

v0.3.12-rc1

v0.3.11

v0.3.11-rc4

v0.3.11-rc3

v0.3.11-rc2

v0.3.11-rc1

v0.3.10

v0.3.10-rc1

v0.3.9

v0.3.8

v0.3.7

v0.3.7-rc6

v0.3.7-rc5

v0.3.7-rc4

v0.3.7-rc3

v0.3.7-rc2

v0.3.7-rc1

v0.3.6

v0.3.5

v0.3.4

v0.3.3

v0.3.2

v0.3.1

v0.3.0

v0.2.8

v0.2.8-rc2

v0.2.8-rc1

v0.2.7

v0.2.6

v0.2.5

v0.2.4

v0.2.3

v0.2.2

v0.2.2-rc2

v0.2.2-rc1

v0.2.1

v0.2.0

v0.1.49-rc14

v0.1.49-rc13

v0.1.49-rc12

v0.1.49-rc11

v0.1.49-rc10

v0.1.49-rc9

v0.1.49-rc8

v0.1.49-rc7

v0.1.49-rc6

v0.1.49-rc4

v0.1.49-rc5

v0.1.49-rc3

v0.1.49-rc2

v0.1.49-rc1

v0.1.48

v0.1.47

v0.1.46

v0.1.45-rc5

v0.1.45

v0.1.45-rc4

v0.1.45-rc3

v0.1.45-rc2

v0.1.45-rc1

v0.1.44

v0.1.43

v0.1.42

v0.1.41

v0.1.40

v0.1.40-rc1

v0.1.39

v0.1.39-rc2

v0.1.39-rc1

v0.1.38

v0.1.37

v0.1.36

v0.1.35

v0.1.35-rc1

v0.1.34

v0.1.34-rc1

v0.1.33

v0.1.33-rc7

v0.1.33-rc6

v0.1.33-rc5

v0.1.33-rc4

v0.1.33-rc3

v0.1.33-rc2

v0.1.33-rc1

v0.1.32

v0.1.32-rc2

v0.1.32-rc1

v0.1.31

v0.1.30

v0.1.29

v0.1.28

v0.1.27

v0.1.26

v0.1.25

v0.1.24

v0.1.23

v0.1.22

v0.1.21

v0.1.20

v0.1.19

v0.1.18

v0.1.17

v0.1.16

v0.1.15

v0.1.14

v0.1.13

v0.1.12

v0.1.11

v0.1.10

v0.1.9

v0.1.8

v0.1.7

v0.1.6

v0.1.5

v0.1.4

v0.1.3

v0.1.2

v0.1.1

v0.1.0

v0.0.21

v0.0.20

v0.0.19

v0.0.18

v0.0.17

v0.0.16

v0.0.15

v0.0.14

v0.0.13

v0.0.12

v0.0.11

v0.0.10

v0.0.9

v0.0.8

v0.0.7

v0.0.6

v0.0.5

v0.0.4

v0.0.3

v0.0.2

v0.0.1

Labels

Clear labels

amd

api

app

bug

build

cli

cloud

compatibility

context-length

create

docker

documentation

embeddings

feature request

feedback wanted

good first issue

gpt-oss

gpu

harmony

help wanted

image

install

intel

js

launch

linux

macos

memory

mlx

model

needs more info

networking

nvidia

ollama.com

performance

pull-request

Mirrored from GitHub Pull Request

python

question

registry

rendering

thinking

tools

top

vulkan

windows

wsl

No Label bug

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

GiteaMirror ninjasurge

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#55438