github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11775] ollama run modelscope.cn/OpenBMB/MiniCPM-V-4-gguf:Q6_K Error: 500 Internal Server Error: llama runner process has terminated: exit status 2 #69863

New Issue
Closed
opened 2026-05-04 19:37:15 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-04 19:37:15 -05:00
Owner
Copy Link

Originally created by @enryteam on GitHub (Aug 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11775

What is the issue?

ollama run modelscope.cn/OpenBMB/MiniCPM-V-4-gguf:Q6_K
Error: 500 Internal Server Error: llama runner process has terminated: exit status 2

BY win10 rtx3060

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @enryteam on GitHub (Aug 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11775 ### What is the issue? ollama run modelscope.cn/OpenBMB/MiniCPM-V-4-gguf:Q6_K Error: 500 Internal Server Error: llama runner process has terminated: exit status 2 BY win10 rtx3060 ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-04 19:37:15 -05:00
GiteaMirror commented 2026-05-04 19:37:21 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 7, 2025):

Server logs will help in debugging.

<!-- gh-comment-id:3162978396 --> @rick-github commented on GitHub (Aug 7, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will help in debugging.
GiteaMirror commented 2026-05-04 19:37:23 -05:00
Author
Owner
Copy Link

@sunskyx commented on GitHub (Aug 7, 2025):

created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3454 +0x485

rax 0x0
rbx 0xa5
rcx 0x71e431e7db2c
rdx 0x6
rdi 0x9e
rsi 0xa5
rbp 0x71e3d3ffe9a0
rsp 0x71e3d3ffe960
r8 0x0
r9 0x0
r10 0x8
r11 0x246
r12 0x6
r13 0xec6
r14 0x16
r15 0xc0006bc000
rip 0x71e431e7db2c
rflags 0x246
cs 0x33
fs 0x0
gs 0x0
time=2025-08-07T13:44:45.651Z level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 2"
[GIN] 2025/08/07 - 13:44:45 | 500 | 2.319104442s | 127.0.0.1 | POST "/api/generate"
time=2025-08-07T13:44:50.651Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.000858676 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=158 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-07T13:44:50.901Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.250288652 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=158 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-07T13:44:51.151Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.500793232 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=158 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
(base) root@ubuntu:# clear
(base) root@ubuntu:# docker logs ollama
time=2025-08-07T13:47:24.094Z level=INFO source=routes.go:1297 msg="server config" env="map[CUDA_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_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-08-07T13:47:24.095Z level=INFO source=images.go:477 msg="total blobs: 61"
time=2025-08-07T13:47:24.096Z level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2025-08-07T13:47:24.096Z level=INFO source=routes.go:1350 msg="Listening on [::]:11434 (version 0.11.3)"
time=2025-08-07T13:47:24.097Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-07T13:47:24.099Z level=INFO source=amd_linux.go:386 msg="amdgpu is supported" gpu=GPU-4a573a50f98400a9 gpu_type=gfx1100
time=2025-08-07T13:47:24.101Z level=INFO source=types.go:130 msg="inference compute" id=GPU-4a573a50f98400a9 library=rocm variant="" compute=gfx1100 driver=6.12 name=1002:744c total="24.0 GiB" available="24.0 GiB"
[GIN] 2025/08/07 - 13:47:34 | 200 | 32.511µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/08/07 - 13:47:34 | 200 | 13.781622ms | 127.0.0.1 | POST "/api/show"
time=2025-08-07T13:47:34.557Z level=INFO source=sched.go:786 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b gpu=GPU-4a573a50f98400a9 parallel=1 available=25725104128 required="3.7 GiB"
time=2025-08-07T13:47:34.557Z level=INFO source=server.go:135 msg="system memory" total="94.0 GiB" free="85.8 GiB" free_swap="8.0 GiB"
time=2025-08-07T13:47:34.557Z level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[24.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="128.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="147.1 MiB" memory.graph.full="284.0 MiB" memory.graph.partial="300.5 MiB" projector.weights="914.3 MiB" projector.graph="0 B"
llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Model
llama_model_loader: - kv 3: general.size_label str = 3.6B
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.context_length u32 = 32768
llama_model_loader: - kv 6: llama.embedding_length u32 = 2560
llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240
llama_model_loader: - kv 8: llama.attention.head_count u32 = 32
llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2
llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 12: llama.attention.key_length u32 = 128
llama_model_loader: - kv 13: llama.attention.value_length u32 = 128
llama_model_loader: - kv 14: llama.vocab_size u32 = 73448
llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 16: tokenizer.ggml.model str = llama
llama_model_loader: - kv 17: tokenizer.ggml.pre str = default
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["", "", "", "", "<C...
llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440
llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 30: general.quantization_version u32 = 2
llama_model_loader: - kv 31: general.file_type u32 = 15
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 2.04 GiB (4.85 BPW)
load: special tokens cache size = 92
load: token to piece cache size = 0.4342 MB
print_info: arch = llama
print_info: vocab_only = 1
print_info: model type = ?B
print_info: model params = 3.61 B
print_info: general.name = Model
print_info: vocab type = SPM
print_info: n_vocab = 73448
print_info: n_merges = 0
print_info: BOS token = 1 ''
print_info: EOS token = 73440 '<|im_end|>'
print_info: EOT token = 73440 '<|im_end|>'
print_info: UNK token = 0 ''
print_info: PAD token = 2 ''
print_info: LF token = 1099 '<0x0A>'
print_info: FIM PRE token = 73445 '<|fim_prefix|>'
print_info: FIM SUF token = 73447 '<|fim_suffix|>'
print_info: FIM MID token = 73446 '<|fim_middle|>'
print_info: EOG token = 73440 '<|im_end|>'
print_info: max token length = 48
llama_model_load: vocab only - skipping tensors
time=2025-08-07T13:47:34.603Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b --ctx-size 4096 --batch-size 512 --n-gpu-layers 33 --threads 6 --parallel 1 --mmproj /root/.ollama/models/blobs/sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761 --port 45783"
time=2025-08-07T13:47:34.603Z level=INFO source=sched.go:481 msg="loaded runners" count=1
time=2025-08-07T13:47:34.603Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-07T13:47:34.603Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-08-07T13:47:34.611Z level=INFO source=runner.go:815 msg="starting go runner"
/opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon Graphics, gfx1100 (0x1100), VMM: no, Wave Size: 32
load_backend: loaded ROCm backend from /usr/lib/ollama/libggml-hip.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so
time=2025-08-07T13:47:35.876Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) - 24524 MiB free
time=2025-08-07T13:47:35.876Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:45783"
llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Model
llama_model_loader: - kv 3: general.size_label str = 3.6B
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.context_length u32 = 32768
llama_model_loader: - kv 6: llama.embedding_length u32 = 2560
llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240
llama_model_loader: - kv 8: llama.attention.head_count u32 = 32
llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2
llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 12: llama.attention.key_length u32 = 128
llama_model_loader: - kv 13: llama.attention.value_length u32 = 128
llama_model_loader: - kv 14: llama.vocab_size u32 = 73448
llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 16: tokenizer.ggml.model str = llama
llama_model_loader: - kv 17: tokenizer.ggml.pre str = default
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["", "", "", "", "<C...
llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440
llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 30: general.quantization_version u32 = 2
llama_model_loader: - kv 31: general.file_type u32 = 15
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 2.04 GiB (4.85 BPW)
load: special tokens cache size = 92
load: token to piece cache size = 0.4342 MB
print_info: arch = llama
print_info: vocab_only = 0
print_info: n_ctx_train = 32768
print_info: n_embd = 2560
print_info: n_layer = 32
print_info: n_head = 32
print_info: n_head_kv = 2
print_info: n_rot = 128
print_info: n_swa = 0
print_info: n_swa_pattern = 1
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 16
print_info: n_embd_k_gqa = 256
print_info: n_embd_v_gqa = 256
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 10240
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 0
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 32768
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 8B
print_info: model params = 3.61 B
print_info: general.name = Model
print_info: vocab type = SPM
print_info: n_vocab = 73448
print_info: n_merges = 0
print_info: BOS token = 1 ''
print_info: EOS token = 73440 '<|im_end|>'
print_info: EOT token = 73440 '<|im_end|>'
print_info: UNK token = 0 ''
print_info: PAD token = 2 ''
print_info: LF token = 1099 '<0x0A>'
print_info: FIM PRE token = 73445 '<|fim_prefix|>'
print_info: FIM SUF token = 73447 '<|fim_suffix|>'
print_info: FIM MID token = 73446 '<|fim_middle|>'
print_info: EOG token = 73440 '<|im_end|>'
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 32 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 33/33 layers to GPU
load_tensors: ROCm0 model buffer size = 1985.93 MiB
load_tensors: CPU_Mapped model buffer size = 100.87 MiB
time=2025-08-07T13:47:36.108Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 512
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: freq_base = 10000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_context: ROCm_Host output buffer size = 0.29 MiB
llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1, padding = 32
llama_kv_cache_unified: ROCm0 KV buffer size = 128.00 MiB
llama_kv_cache_unified: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB
llama_context: ROCm0 compute buffer size = 290.00 MiB
llama_context: ROCm_Host compute buffer size = 13.01 MiB
llama_context: graph nodes = 1094
llama_context: graph splits = 2
clip_ctx: CLIP using ROCm0 backend
clip_model_loader: model name:
clip_model_loader: description: image encoder for MiniCPM-V
clip_model_loader: GGUF version: 3
clip_model_loader: alignment: 32
clip_model_loader: n_tensors: 455
clip_model_loader: n_kv: 19

clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=655360, offset=0, shape:[2560, 64, 1, 1], type = f32
clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=50176000, offset=655360, shape:[2560, 4900, 1, 1], type = f32
clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=13107200, offset=50831360, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=5898240, offset=63938560, shape:[1152, 2560, 1, 1], type = f16
clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=13107200, offset=69836800, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=13107200, offset=82944000, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=13107200, offset=96051200, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=10240, offset=109158400, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=10240, offset=109168640, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=10240, offset=109178880, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=13107200, offset=109189120, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=10240, offset=122296320, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=10240, offset=122306560, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=10240, offset=122316800, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=10240, offset=122327040, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=10240, offset=122337280, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=10240, offset=122347520, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=10240, offset=122357760, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=122368000, shape:[14, 14, 3, 1152], type = f16
clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=123722752, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=123727360, shape:[1152, 4900, 1, 1], type = f16
clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=135016960, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=137671168, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=137675776, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=140329984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=140334592, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=142988800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=142993408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=145647616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=145652224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=145656832, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=145661440, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=155577856, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=155595072, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=165511488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=165516096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=165520704, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=165525312, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=168179520, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=168184128, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=170838336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=170842944, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=173497152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=173501760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=176155968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=176160576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=176165184, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=176169792, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=186086208, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=186103424, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=196019840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=196024448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=196029056, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=196033664, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=198687872, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=198692480, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=201346688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=201351296, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=204005504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=204010112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=206664320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=206668928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=206673536, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=206678144, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=216594560, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=216611776, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=226528192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=226532800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=226537408, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=226542016, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=229196224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=229200832, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=231855040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=231859648, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=234513856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=234518464, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=237172672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=237177280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=237181888, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=237186496, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=247102912, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=247120128, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=257036544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=257041152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=257045760, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=257050368, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=259704576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=259709184, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=262363392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=262368000, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=265022208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=265026816, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=267681024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=267685632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=267690240, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=267694848, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=277611264, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=277628480, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=287544896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=287549504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=287554112, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=287558720, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=290212928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=290217536, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=292871744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=292876352, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=295530560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=295535168, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=298189376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=298193984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=298198592, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=298203200, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=308119616, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=308136832, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=318053248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=318057856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=318062464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=318067072, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=320721280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=320725888, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=323380096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=323384704, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=326038912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=326043520, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=328697728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=328702336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=328706944, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=328711552, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=338627968, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=338645184, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=348561600, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=348566208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=348570816, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=348575424, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=351229632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=351234240, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=353888448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=353893056, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=356547264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=356551872, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=359206080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=359210688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=359215296, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=359219904, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=369136320, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=369153536, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=379069952, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=379074560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=379079168, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=379083776, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=381737984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=381742592, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=384396800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=384401408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=387055616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=387060224, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=389714432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=389719040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=389723648, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=389728256, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=399644672, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=399661888, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=409578304, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=409582912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=409587520, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=409592128, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=412246336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=412250944, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=414905152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=414909760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=417563968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=417568576, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=420222784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=420227392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=420232000, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=420236608, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=430153024, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=430170240, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=440086656, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=440091264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=440095872, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=440100480, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=442754688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=442759296, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=445413504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=445418112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=448072320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=448076928, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=450731136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=450735744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=450740352, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=450744960, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=460661376, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=460678592, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=470595008, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=470599616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=470604224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=470608832, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=473263040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=473267648, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=475921856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=475926464, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=478580672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=478585280, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=481239488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=481244096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=481248704, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=481253312, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=491169728, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=491186944, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=501103360, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=501107968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=501112576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=501117184, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=503771392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=503776000, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=506430208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=506434816, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=509089024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=509093632, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=511747840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=511752448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=511757056, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=511761664, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=521678080, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=521695296, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=531611712, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=531616320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=531620928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=531625536, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=534279744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=534284352, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=536938560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=536943168, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=539597376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=539601984, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=542256192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=542260800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=542265408, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=542270016, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=552186432, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=552203648, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=562120064, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=562124672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=562129280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=562133888, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=564788096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=564792704, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=567446912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=567451520, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=570105728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=570110336, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=572764544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=572769152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=572773760, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=572778368, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=582694784, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=582712000, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=592628416, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=592633024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=592637632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=592642240, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=595296448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=595301056, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=597955264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=597959872, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=600614080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=600618688, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=603272896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=603277504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=603282112, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=603286720, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=613203136, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=613220352, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=623136768, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=623141376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=623145984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=623150592, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=625804800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=625809408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=628463616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=628468224, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=631122432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=631127040, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=633781248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=633785856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=633790464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=633795072, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=643711488, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=643728704, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=653645120, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=653649728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=653654336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=653658944, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=656313152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=656317760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=658971968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=658976576, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=661630784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=661635392, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=664289600, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=664294208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=664298816, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=664303424, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=674219840, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=674237056, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=684153472, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=684158080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=684162688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=684167296, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=686821504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=686826112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=689480320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=689484928, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=692139136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=692143744, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=694797952, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=694802560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=694807168, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=694811776, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=704728192, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=704745408, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=714661824, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=714666432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=714671040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=714675648, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=717329856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=717334464, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=719988672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=719993280, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=722647488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=722652096, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=725306304, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=725310912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=725315520, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=725320128, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=735236544, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=735253760, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=745170176, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=745174784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=745179392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=745184000, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=747838208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=747842816, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=750497024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=750501632, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=753155840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=753160448, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=755814656, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=755819264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=755823872, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=755828480, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=765744896, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=765762112, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=775678528, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=775683136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=775687744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=775692352, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=778346560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=778351168, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=781005376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=781009984, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=783664192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=783668800, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=786323008, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=786327616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=786332224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=786336832, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=796253248, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=796270464, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=806186880, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=806191488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=806196096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=806200704, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=808854912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=808859520, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=811513728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=811518336, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=814172544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=814177152, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=816831360, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=816835968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=816840576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=816845184, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=826761600, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=826778816, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=836695232, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=836699840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=836704448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=836709056, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=839363264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=839367872, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=842022080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=842026688, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=844680896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=844685504, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=847339712, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=847344320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=847348928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=847353536, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=857269952, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=857287168, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=867203584, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=867208192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=867212800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=867217408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=869871616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=869876224, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=872530432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=872535040, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=875189248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=875193856, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=877848064, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=877852672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=877857280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=877861888, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=887778304, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=887795520, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=897711936, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=897716544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=897721152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=897725760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=900379968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=900384576, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=903038784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=903043392, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=905697600, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=905702208, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=908356416, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=908361024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=908365632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=908370240, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=918286656, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=918303872, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=928220288, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=928224896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=928229504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=928234112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=930888320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=930892928, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=933547136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=933551744, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=936205952, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=936210560, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=938864768, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=938869376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=938873984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=938878592, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=948795008, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=948812224, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=958728640, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=958733248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=958737856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=958742464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=958747072, shape:[1152, 1, 1, 1], type = f32
load_hparams: projector: resampler
load_hparams: n_embd: 1152
load_hparams: n_head: 16
load_hparams: n_ff: 4304
load_hparams: n_layer: 27
load_hparams: projection_dim: 0
load_hparams: image_size: 448
load_hparams: patch_size: 14

load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 5
load_hparams: proj_scale_factor: 0
load_hparams: n_wa_pattern: 0
load_hparams: ffn_op: gelu
load_hparams: model size: 914.34 MiB
load_hparams: metadata size: 0.16 MiB
load_tensors: loaded 455 tensors from /root/.ollama/models/blobs/sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761
clip.cpp:3782: Unknown minicpmv version
Memory critical error by agent node-0 (Agent handle: 0x59ba7d536b40) on address 0x79a845f00000. Reason: Memory in use.
SIGABRT: abort
PC=0x79aa526d7b2c m=5 sigcode=18446744073709551610
signal arrived during cgo execution

goroutine 10 gp=0xc000505180 m=5 mp=0xc000100008 [syscall]:
runtime.cgocall(0x59ba7578a080, 0xc00008bc58)
runtime/cgocall.go:167 +0x4b fp=0xc00008bc30 sp=0xc00008bbf8 pc=0x59ba74ab98cb
github.com/ollama/ollama/llama._Cfunc_clip_model_load(0x79a9f59354f0, 0x1)
_cgo_gotypes.go:315 +0x4b fp=0xc00008bc58 sp=0xc00008bc30 pc=0x59ba74e6706b
github.com/ollama/ollama/llama.NewClipContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62})
github.com/ollama/ollama/llama/llama.go:470 +0x90 fp=0xc00008bd18 sp=0xc00008bc58 pc=0x59ba74e6cbd0
github.com/ollama/ollama/runner/llamarunner.NewImageContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62})
github.com/ollama/ollama/runner/llamarunner/image.go:35 +0x105 fp=0xc00008bd98 sp=0xc00008bd18 pc=0x59ba74f23e05
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0004e4360, {0x21, 0x0, 0x1, {0x0, 0x0, 0x0}, 0xc000045940, 0x0}, {0x7ffda9dddcf7, ...}, ...)
github.com/ollama/ollama/runner/llamarunner/runner.go:771 +0x248 fp=0xc00008bee0 sp=0xc00008bd98 pc=0x59ba74f28e68
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0x175 fp=0xc00008bfe0 sp=0xc00008bee0 pc=0x59ba74f2a4d5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00008bfe8 sp=0xc00008bfe0 pc=0x59ba74ac4481
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0xb57

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000525608 sp=0xc0005255e8 pc=0x59ba74abcd4e
runtime.netpollblock(0xc000525688?, 0x74a55b46?, 0xba?)
runtime/netpoll.go:575 +0xf7 fp=0xc000525640 sp=0xc000525608 pc=0x59ba74a81837
internal/poll.runtime_pollWait(0x79aa5246aeb0, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc000525660 sp=0xc000525640 pc=0x59ba74abbf65
internal/poll.(*pollDesc).wait(0xc0001cdb80?, 0x59ba74a64546?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000525688 sp=0xc000525660 pc=0x59ba74b433a7
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0001cdb80)
internal/poll/fd_unix.go:620 +0x295 fp=0xc000525730 sp=0xc000525688 pc=0x59ba74b48775
net.(*netFD).accept(0xc0001cdb80)
net/fd_unix.go:172 +0x29 fp=0xc0005257e8 sp=0xc000525730 pc=0x59ba74bbad89
net.(*TCPListener).accept(0xc0002e4340)
net/tcpsock_posix.go:159 +0x1b fp=0xc000525838 sp=0xc0005257e8 pc=0x59ba74bd073b
net.(*TCPListener).Accept(0xc0002e4340)
net/tcpsock.go:380 +0x30 fp=0xc000525868 sp=0xc000525838 pc=0x59ba74bcf5f0
net/http.(*onceCloseListener).Accept(0xc00053c000?)
:1 +0x24 fp=0xc000525880 sp=0xc000525868 pc=0x59ba74de6d44
net/http.(*Server).Serve(0xc00051d500, {0x59ba75e302e8, 0xc0002e4340})
net/http/server.go:3424 +0x30c fp=0xc0005259b0 sp=0xc000525880 pc=0x59ba74dbe60c
github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034140, 0x10, 0x10})
github.com/ollama/ollama/runner/llamarunner/runner.go:875 +0x100a fp=0xc000525d08 sp=0xc0005259b0 pc=0x59ba74f2a06a
github.com/ollama/ollama/runner.Execute({0xc000034130?, 0x0?, 0x0?})
github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000525d30 sp=0xc000525d08 pc=0x59ba74fb3934
github.com/ollama/ollama/cmd.NewCLI.func2(0xc00051d000?, {0x59ba7597307e?, 0x4?, 0x59ba75973082?})
github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000525d58 sp=0xc000525d30 pc=0x59ba75718685
github.com/spf13/cobra.(*Command).execute(0xc0004e6f08, {0xc00051d200, 0x10, 0x10})
github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000525e78 sp=0xc000525d58 pc=0x59ba74c343dc
github.com/spf13/cobra.(*Command).ExecuteC(0xc000494f08)
github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000525f30 sp=0xc000525e78 pc=0x59ba74c34c25
github.com/spf13/cobra.(*Command).Execute(...)
github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000525f50 sp=0xc000525f30 pc=0x59ba7571916d
runtime.main()
runtime/proc.go:283 +0x29d fp=0xc000525fe0 sp=0xc000525f50 pc=0x59ba74a88ebd
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000525fe8 sp=0xc000525fe0 pc=0x59ba74ac4481

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000072fa8 sp=0xc000072f88 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.forcegchelper()
runtime/proc.go:348 +0xb8 fp=0xc000072fe0 sp=0xc000072fa8 pc=0x59ba74a891f8
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x59ba74ac4481
created by runtime.init.7 in goroutine 1
runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000073780 sp=0xc000073760 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.bgsweep(0xc00007e000)
runtime/mgcsweep.go:316 +0xdf fp=0xc0000737c8 sp=0xc000073780 pc=0x59ba74a7399f
runtime.gcenable.gowrap1()
runtime/mgc.go:204 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x59ba74a67d85
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x59ba74ac4481
created by runtime.gcenable in goroutine 1
runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x59ba75b35158?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000073f78 sp=0xc000073f58 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.(*scavengerState).park(0x59ba766c79a0)
runtime/mgcscavenge.go:425 +0x49 fp=0xc000073fa8 sp=0xc000073f78 pc=0x59ba74a713e9
runtime.bgscavenge(0xc00007e000)
runtime/mgcscavenge.go:658 +0x59 fp=0xc000073fc8 sp=0xc000073fa8 pc=0x59ba74a71979
runtime.gcenable.gowrap2()
runtime/mgc.go:205 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x59ba74a67d25
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x59ba74ac4481
created by runtime.gcenable in goroutine 1
runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000072688?)
runtime/proc.go:435 +0xce fp=0xc000072630 sp=0xc000072610 pc=0x59ba74abcd4e
runtime.runfinq()
runtime/mfinal.go:196 +0x107 fp=0xc0000727e0 sp=0xc000072630 pc=0x59ba74a66d47
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x59ba74ac4481
created by runtime.createfing in goroutine 1
runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]:
runtime.gopark(0xc000225860?, 0xc000590018?, 0x60?, 0x47?, 0x59ba74ba19c8?)
runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x59ba74abcd4e
runtime.chanrecv(0xc0000aa310, 0x0, 0x1)
runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x59ba74a58725
runtime.chanrecv1(0x0?, 0x0?)
runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x59ba74a582b2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
runtime/mgc.go:1799 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x59ba74a6af2f
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x59ba74ac4481
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0001d1180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006ef38 sp=0xc00006ef18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006efc8 sp=0xc00006ef38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006efe0 sp=0xc00006efc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0001d1340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006f738 sp=0xc00006f718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006f7c8 sp=0xc00006f738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0001d1500 m=nil [GC worker (idle)]:
runtime.gopark(0x508351928f82?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000075f38 sp=0xc000075f18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc000075fc8 sp=0xc000075f38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000075fe0 sp=0xc000075fc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000075fe8 sp=0xc000075fe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000504700 m=nil [GC worker (idle)]:
runtime.gopark(0x508351921eb8?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc0005048c0 m=nil [GC worker (idle)]:
runtime.gopark(0x508351921f94?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc000504a80 m=nil [GC worker (idle)]:
runtime.gopark(0x508351923a9f?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc0001028c0 m=nil [GC worker (idle)]:
runtime.gopark(0x508351928bf2?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006ff38 sp=0xc00006ff18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006ffc8 sp=0xc00006ff38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006ffe0 sp=0xc00006ffc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 11 gp=0xc000505340 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x60?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050ce20 sp=0xc00050ce00 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.semacquire1(0xc0004e4368, 0x0, 0x1, 0x0, 0x18)
runtime/sema.go:188 +0x229 fp=0xc00050ce88 sp=0xc00050ce20 pc=0x59ba74a9c489
sync.runtime_SemacquireWaitGroup(0x0?)
runtime/sema.go:110 +0x25 fp=0xc00050cec0 sp=0xc00050ce88 pc=0x59ba74abe765
sync.(*WaitGroup).Wait(0x0?)
sync/waitgroup.go:118 +0x48 fp=0xc00050cee8 sp=0xc00050cec0 pc=0x59ba74acfdc8
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0004e4360, {0x59ba75e32790, 0xc0000f4af0})
github.com/ollama/ollama/runner/llamarunner/runner.go:314 +0x47 fp=0xc00050cfb8 sp=0xc00050cee8 pc=0x59ba74f259e7
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2()
github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0x28 fp=0xc00050cfe0 sp=0xc00050cfb8 pc=0x59ba74f2a328
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050cfe8 sp=0xc00050cfe0 pc=0x59ba74ac4481
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0xc37

goroutine 39 gp=0xc000102a80 m=nil [IO wait]:
runtime.gopark(0x59ba74b469a5?, 0xc000474000?, 0x40?, 0x9a?, 0xb?)
runtime/proc.go:435 +0xce fp=0xc000129948 sp=0xc000129928 pc=0x59ba74abcd4e
runtime.netpollblock(0x59ba74ae00b8?, 0x74a55b46?, 0xba?)
runtime/netpoll.go:575 +0xf7 fp=0xc000129980 sp=0xc000129948 pc=0x59ba74a81837
internal/poll.runtime_pollWait(0x79aa5246ad98, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0001299a0 sp=0xc000129980 pc=0x59ba74abbf65
internal/poll.(*pollDesc).wait(0xc000474000?, 0xc0004fe000?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001299c8 sp=0xc0001299a0 pc=0x59ba74b433a7
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc000474000, {0xc0004fe000, 0x1000, 0x1000})
internal/poll/fd_unix.go:165 +0x27a fp=0xc000129a60 sp=0xc0001299c8 pc=0x59ba74b4469a
net.(*netFD).Read(0xc000474000, {0xc0004fe000?, 0xc000129ad0?, 0x59ba74b43865?})
net/fd_posix.go:55 +0x25 fp=0xc000129aa8 sp=0xc000129a60 pc=0x59ba74bb8de5
net.(*conn).Read(0xc00053a000, {0xc0004fe000?, 0x0?, 0x0?})
net/net.go:194 +0x45 fp=0xc000129af0 sp=0xc000129aa8 pc=0x59ba74bc71a5
net/http.(*connReader).Read(0xc0004f8090, {0xc0004fe000, 0x1000, 0x1000})
net/http/server.go:798 +0x159 fp=0xc000129b40 sp=0xc000129af0 pc=0x59ba74db34b9
bufio.(*Reader).fill(0xc000110660)
bufio/bufio.go:113 +0x103 fp=0xc000129b78 sp=0xc000129b40 pc=0x59ba74bde943
bufio.(*Reader).Peek(0xc000110660, 0x4)
bufio/bufio.go:152 +0x53 fp=0xc000129b98 sp=0xc000129b78 pc=0x59ba74bdea73
net/http.(*conn).serve(0xc00053c000, {0x59ba75e32758, 0xc0004f8030})
net/http/server.go:2137 +0x785 fp=0xc000129fb8 sp=0xc000129b98 pc=0x59ba74db92a5
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3454 +0x28 fp=0xc000129fe0 sp=0xc000129fb8 pc=0x59ba74dbea08
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000129fe8 sp=0xc000129fe0 pc=0x59ba74ac4481
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3454 +0x485

rax 0x0
rbx 0x33
rcx 0x79aa526d7b2c
rdx 0x6
rdi 0x33
rsi 0x33
rbp 0x79aa0a2fb720
rsp 0x79aa0a2fb6e0
r8 0x78
r9 0x0
r10 0x8
r11 0x246
r12 0x6
r13 0x0
r14 0x16
r15 0x0
rip 0x79aa526d7b2c
rflags 0x246
cs 0x33
fs 0x0
gs 0x0
SIGABRT: abort
PC=0x79aa526d7b2c m=5 sigcode=18446744073709551610
signal arrived during cgo execution

goroutine 10 gp=0xc000505180 m=5 mp=0xc000100008 [syscall]:
runtime.cgocall(0x59ba7578a080, 0xc00008bc58)
runtime/cgocall.go:167 +0x4b fp=0xc00008bc30 sp=0xc00008bbf8 pc=0x59ba74ab98cb
github.com/ollama/ollama/llama._Cfunc_clip_model_load(0x79a9f59354f0, 0x1)
_cgo_gotypes.go:315 +0x4b fp=0xc00008bc58 sp=0xc00008bc30 pc=0x59ba74e6706b
github.com/ollama/ollama/llama.NewClipContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62})
github.com/ollama/ollama/llama/llama.go:470 +0x90 fp=0xc00008bd18 sp=0xc00008bc58 pc=0x59ba74e6cbd0
github.com/ollama/ollama/runner/llamarunner.NewImageContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62})
github.com/ollama/ollama/runner/llamarunner/image.go:35 +0x105 fp=0xc00008bd98 sp=0xc00008bd18 pc=0x59ba74f23e05
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0004e4360, {0x21, 0x0, 0x1, {0x0, 0x0, 0x0}, 0xc000045940, 0x0}, {0x7ffda9dddcf7, ...}, ...)
github.com/ollama/ollama/runner/llamarunner/runner.go:771 +0x248 fp=0xc00008bee0 sp=0xc00008bd98 pc=0x59ba74f28e68
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0x175 fp=0xc00008bfe0 sp=0xc00008bee0 pc=0x59ba74f2a4d5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00008bfe8 sp=0xc00008bfe0 pc=0x59ba74ac4481
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0xb57

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000525608 sp=0xc0005255e8 pc=0x59ba74abcd4e
runtime.netpollblock(0xc000525688?, 0x74a55b46?, 0xba?)
runtime/netpoll.go:575 +0xf7 fp=0xc000525640 sp=0xc000525608 pc=0x59ba74a81837
internal/poll.runtime_pollWait(0x79aa5246aeb0, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc000525660 sp=0xc000525640 pc=0x59ba74abbf65
internal/poll.(*pollDesc).wait(0xc0001cdb80?, 0x59ba74a64546?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000525688 sp=0xc000525660 pc=0x59ba74b433a7
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0001cdb80)
internal/poll/fd_unix.go:620 +0x295 fp=0xc000525730 sp=0xc000525688 pc=0x59ba74b48775
net.(*netFD).accept(0xc0001cdb80)
net/fd_unix.go:172 +0x29 fp=0xc0005257e8 sp=0xc000525730 pc=0x59ba74bbad89
net.(*TCPListener).accept(0xc0002e4340)
net/tcpsock_posix.go:159 +0x1b fp=0xc000525838 sp=0xc0005257e8 pc=0x59ba74bd073b
net.(*TCPListener).Accept(0xc0002e4340)
net/tcpsock.go:380 +0x30 fp=0xc000525868 sp=0xc000525838 pc=0x59ba74bcf5f0
net/http.(*onceCloseListener).Accept(0xc00053c000?)
:1 +0x24 fp=0xc000525880 sp=0xc000525868 pc=0x59ba74de6d44
net/http.(*Server).Serve(0xc00051d500, {0x59ba75e302e8, 0xc0002e4340})
net/http/server.go:3424 +0x30c fp=0xc0005259b0 sp=0xc000525880 pc=0x59ba74dbe60c
github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034140, 0x10, 0x10})
github.com/ollama/ollama/runner/llamarunner/runner.go:875 +0x100a fp=0xc000525d08 sp=0xc0005259b0 pc=0x59ba74f2a06a
github.com/ollama/ollama/runner.Execute({0xc000034130?, 0x0?, 0x0?})
github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000525d30 sp=0xc000525d08 pc=0x59ba74fb3934
github.com/ollama/ollama/cmd.NewCLI.func2(0xc00051d000?, {0x59ba7597307e?, 0x4?, 0x59ba75973082?})
github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000525d58 sp=0xc000525d30 pc=0x59ba75718685
github.com/spf13/cobra.(*Command).execute(0xc0004e6f08, {0xc00051d200, 0x10, 0x10})
github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000525e78 sp=0xc000525d58 pc=0x59ba74c343dc
github.com/spf13/cobra.(*Command).ExecuteC(0xc000494f08)
github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000525f30 sp=0xc000525e78 pc=0x59ba74c34c25
github.com/spf13/cobra.(*Command).Execute(...)
github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000525f50 sp=0xc000525f30 pc=0x59ba7571916d
runtime.main()
runtime/proc.go:283 +0x29d fp=0xc000525fe0 sp=0xc000525f50 pc=0x59ba74a88ebd
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000525fe8 sp=0xc000525fe0 pc=0x59ba74ac4481

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000072fa8 sp=0xc000072f88 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.forcegchelper()
runtime/proc.go:348 +0xb8 fp=0xc000072fe0 sp=0xc000072fa8 pc=0x59ba74a891f8
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x59ba74ac4481
created by runtime.init.7 in goroutine 1
runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000073780 sp=0xc000073760 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.bgsweep(0xc00007e000)
runtime/mgcsweep.go:316 +0xdf fp=0xc0000737c8 sp=0xc000073780 pc=0x59ba74a7399f
runtime.gcenable.gowrap1()
runtime/mgc.go:204 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x59ba74a67d85
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x59ba74ac4481
created by runtime.gcenable in goroutine 1
runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x59ba75b35158?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000073f78 sp=0xc000073f58 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.(*scavengerState).park(0x59ba766c79a0)
runtime/mgcscavenge.go:425 +0x49 fp=0xc000073fa8 sp=0xc000073f78 pc=0x59ba74a713e9
runtime.bgscavenge(0xc00007e000)
runtime/mgcscavenge.go:658 +0x59 fp=0xc000073fc8 sp=0xc000073fa8 pc=0x59ba74a71979
runtime.gcenable.gowrap2()
runtime/mgc.go:205 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x59ba74a67d25
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x59ba74ac4481
created by runtime.gcenable in goroutine 1
runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000072688?)
runtime/proc.go:435 +0xce fp=0xc000072630 sp=0xc000072610 pc=0x59ba74abcd4e
runtime.runfinq()
runtime/mfinal.go:196 +0x107 fp=0xc0000727e0 sp=0xc000072630 pc=0x59ba74a66d47
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x59ba74ac4481
created by runtime.createfing in goroutine 1
runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]:
runtime.gopark(0xc000225860?, 0xc000590018?, 0x60?, 0x47?, 0x59ba74ba19c8?)
runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x59ba74abcd4e
runtime.chanrecv(0xc0000aa310, 0x0, 0x1)
runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x59ba74a58725
runtime.chanrecv1(0x0?, 0x0?)
runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x59ba74a582b2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
runtime/mgc.go:1799 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x59ba74a6af2f
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x59ba74ac4481
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0001d1180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006ef38 sp=0xc00006ef18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006efc8 sp=0xc00006ef38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006efe0 sp=0xc00006efc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0001d1340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006f738 sp=0xc00006f718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006f7c8 sp=0xc00006f738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0001d1500 m=nil [GC worker (idle)]:
runtime.gopark(0x508351928f82?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000075f38 sp=0xc000075f18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc000075fc8 sp=0xc000075f38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000075fe0 sp=0xc000075fc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000075fe8 sp=0xc000075fe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000504700 m=nil [GC worker (idle)]:
runtime.gopark(0x508351921eb8?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc0005048c0 m=nil [GC worker (idle)]:
runtime.gopark(0x508351921f94?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc000504a80 m=nil [GC worker (idle)]:
runtime.gopark(0x508351923a9f?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc0001028c0 m=nil [GC worker (idle)]:
runtime.gopark(0x508351928bf2?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00006ff38 sp=0xc00006ff18 pc=0x59ba74abcd4e
runtime.gcBgMarkWorker(0xc0000ab730)
runtime/mgc.go:1423 +0xe9 fp=0xc00006ffc8 sp=0xc00006ff38 pc=0x59ba74a6a249
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00006ffe0 sp=0xc00006ffc8 pc=0x59ba74a6a125
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x59ba74ac4481
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 11 gp=0xc000505340 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x60?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc00050ce20 sp=0xc00050ce00 pc=0x59ba74abcd4e
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.semacquire1(0xc0004e4368, 0x0, 0x1, 0x0, 0x18)
runtime/sema.go:188 +0x229 fp=0xc00050ce88 sp=0xc00050ce20 pc=0x59ba74a9c489
sync.runtime_SemacquireWaitGroup(0x0?)
runtime/sema.go:110 +0x25 fp=0xc00050cec0 sp=0xc00050ce88 pc=0x59ba74abe765
sync.(*WaitGroup).Wait(0x0?)
sync/waitgroup.go:118 +0x48 fp=0xc00050cee8 sp=0xc00050cec0 pc=0x59ba74acfdc8
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0004e4360, {0x59ba75e32790, 0xc0000f4af0})
github.com/ollama/ollama/runner/llamarunner/runner.go:314 +0x47 fp=0xc00050cfb8 sp=0xc00050cee8 pc=0x59ba74f259e7
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2()
github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0x28 fp=0xc00050cfe0 sp=0xc00050cfb8 pc=0x59ba74f2a328
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00050cfe8 sp=0xc00050cfe0 pc=0x59ba74ac4481
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0xc37

goroutine 39 gp=0xc000102a80 m=nil [IO wait]:
runtime.gopark(0x59ba74b469a5?, 0xc000474000?, 0x40?, 0x9a?, 0xb?)
runtime/proc.go:435 +0xce fp=0xc000129948 sp=0xc000129928 pc=0x59ba74abcd4e
runtime.netpollblock(0x59ba74ae00b8?, 0x74a55b46?, 0xba?)
runtime/netpoll.go:575 +0xf7 fp=0xc000129980 sp=0xc000129948 pc=0x59ba74a81837
internal/poll.runtime_pollWait(0x79aa5246ad98, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0001299a0 sp=0xc000129980 pc=0x59ba74abbf65
internal/poll.(*pollDesc).wait(0xc000474000?, 0xc0004fe000?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001299c8 sp=0xc0001299a0 pc=0x59ba74b433a7
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc000474000, {0xc0004fe000, 0x1000, 0x1000})
internal/poll/fd_unix.go:165 +0x27a fp=0xc000129a60 sp=0xc0001299c8 pc=0x59ba74b4469a
net.(*netFD).Read(0xc000474000, {0xc0004fe000?, 0xc000129ad0?, 0x59ba74b43865?})
net/fd_posix.go:55 +0x25 fp=0xc000129aa8 sp=0xc000129a60 pc=0x59ba74bb8de5
net.(*conn).Read(0xc00053a000, {0xc0004fe000?, 0x0?, 0x0?})
net/net.go:194 +0x45 fp=0xc000129af0 sp=0xc000129aa8 pc=0x59ba74bc71a5
net/http.(*connReader).Read(0xc0004f8090, {0xc0004fe000, 0x1000, 0x1000})
net/http/server.go:798 +0x159 fp=0xc000129b40 sp=0xc000129af0 pc=0x59ba74db34b9
bufio.(*Reader).fill(0xc000110660)
bufio/bufio.go:113 +0x103 fp=0xc000129b78 sp=0xc000129b40 pc=0x59ba74bde943
bufio.(*Reader).Peek(0xc000110660, 0x4)
bufio/bufio.go:152 +0x53 fp=0xc000129b98 sp=0xc000129b78 pc=0x59ba74bdea73
net/http.(*conn).serve(0xc00053c000, {0x59ba75e32758, 0xc0004f8030})
net/http/server.go:2137 +0x785 fp=0xc000129fb8 sp=0xc000129b98 pc=0x59ba74db92a5
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3454 +0x28 fp=0xc000129fe0 sp=0xc000129fb8 pc=0x59ba74dbea08
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000129fe8 sp=0xc000129fe0 pc=0x59ba74ac4481
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3454 +0x485

rax 0x0
rbx 0x2b
rcx 0x79aa526d7b2c
rdx 0x6
rdi 0x27
rsi 0x2b
rbp 0x79aa0a2fb9a0
rsp 0x79aa0a2fb960
r8 0x0
r9 0x0
r10 0x8
r11 0x246
r12 0x6
r13 0xec6
r14 0x16
r15 0xc0000da000
rip 0x79aa526d7b2c
rflags 0x246
cs 0x33
fs 0x0
gs 0x0
time=2025-08-07T13:47:36.860Z level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 2"
[GIN] 2025/08/07 - 13:47:36 | 500 | 2.32287378s | 127.0.0.1 | POST "/api/generate"
time=2025-08-07T13:47:41.861Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.000299103 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=39 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-07T13:47:42.111Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.25111742 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=39 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-07T13:47:42.361Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.50081186 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=39 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b

<!-- gh-comment-id:3164282304 --> @sunskyx commented on GitHub (Aug 7, 2025): created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 rax 0x0 rbx 0xa5 rcx 0x71e431e7db2c rdx 0x6 rdi 0x9e rsi 0xa5 rbp 0x71e3d3ffe9a0 rsp 0x71e3d3ffe960 r8 0x0 r9 0x0 r10 0x8 r11 0x246 r12 0x6 r13 0xec6 r14 0x16 r15 0xc0006bc000 rip 0x71e431e7db2c rflags 0x246 cs 0x33 fs 0x0 gs 0x0 time=2025-08-07T13:44:45.651Z level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 2" [GIN] 2025/08/07 - 13:44:45 | 500 | 2.319104442s | 127.0.0.1 | POST "/api/generate" time=2025-08-07T13:44:50.651Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.000858676 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=158 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b time=2025-08-07T13:44:50.901Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.250288652 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=158 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b time=2025-08-07T13:44:51.151Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.500793232 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=158 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (base) root@ubuntu:~# clear (base) root@ubuntu:~# docker logs ollama time=2025-08-07T13:47:24.094Z level=INFO source=routes.go:1297 msg="server config" env="map[CUDA_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_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-08-07T13:47:24.095Z level=INFO source=images.go:477 msg="total blobs: 61" time=2025-08-07T13:47:24.096Z level=INFO source=images.go:484 msg="total unused blobs removed: 0" time=2025-08-07T13:47:24.096Z level=INFO source=routes.go:1350 msg="Listening on [::]:11434 (version 0.11.3)" time=2025-08-07T13:47:24.097Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-07T13:47:24.099Z level=INFO source=amd_linux.go:386 msg="amdgpu is supported" gpu=GPU-4a573a50f98400a9 gpu_type=gfx1100 time=2025-08-07T13:47:24.101Z level=INFO source=types.go:130 msg="inference compute" id=GPU-4a573a50f98400a9 library=rocm variant="" compute=gfx1100 driver=6.12 name=1002:744c total="24.0 GiB" available="24.0 GiB" [GIN] 2025/08/07 - 13:47:34 | 200 | 32.511µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/07 - 13:47:34 | 200 | 13.781622ms | 127.0.0.1 | POST "/api/show" time=2025-08-07T13:47:34.557Z level=INFO source=sched.go:786 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b gpu=GPU-4a573a50f98400a9 parallel=1 available=25725104128 required="3.7 GiB" time=2025-08-07T13:47:34.557Z level=INFO source=server.go:135 msg="system memory" total="94.0 GiB" free="85.8 GiB" free_swap="8.0 GiB" time=2025-08-07T13:47:34.557Z level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[24.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="128.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="147.1 MiB" memory.graph.full="284.0 MiB" memory.graph.partial="300.5 MiB" projector.weights="914.3 MiB" projector.graph="0 B" llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Model llama_model_loader: - kv 3: general.size_label str = 3.6B llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.context_length u32 = 32768 llama_model_loader: - kv 6: llama.embedding_length u32 = 2560 llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240 llama_model_loader: - kv 8: llama.attention.head_count u32 = 32 llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 12: llama.attention.key_length u32 = 128 llama_model_loader: - kv 13: llama.attention.value_length u32 = 128 llama_model_loader: - kv 14: llama.vocab_size u32 = 73448 llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 16: tokenizer.ggml.model str = llama llama_model_loader: - kv 17: tokenizer.ggml.pre str = default llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["<unk>", "<s>", "</s>", "<SEP>", "<C... llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440 llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 30: general.quantization_version u32 = 2 llama_model_loader: - kv 31: general.file_type u32 = 15 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 2.04 GiB (4.85 BPW) load: special tokens cache size = 92 load: token to piece cache size = 0.4342 MB print_info: arch = llama print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 3.61 B print_info: general.name = Model print_info: vocab type = SPM print_info: n_vocab = 73448 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 73440 '<|im_end|>' print_info: EOT token = 73440 '<|im_end|>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 2 '</s>' print_info: LF token = 1099 '<0x0A>' print_info: FIM PRE token = 73445 '<|fim_prefix|>' print_info: FIM SUF token = 73447 '<|fim_suffix|>' print_info: FIM MID token = 73446 '<|fim_middle|>' print_info: EOG token = 73440 '<|im_end|>' print_info: max token length = 48 llama_model_load: vocab only - skipping tensors time=2025-08-07T13:47:34.603Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b --ctx-size 4096 --batch-size 512 --n-gpu-layers 33 --threads 6 --parallel 1 --mmproj /root/.ollama/models/blobs/sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761 --port 45783" time=2025-08-07T13:47:34.603Z level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-07T13:47:34.603Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-07T13:47:34.603Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-07T13:47:34.611Z level=INFO source=runner.go:815 msg="starting go runner" /opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon Graphics, gfx1100 (0x1100), VMM: no, Wave Size: 32 load_backend: loaded ROCm backend from /usr/lib/ollama/libggml-hip.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so time=2025-08-07T13:47:35.876Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) - 24524 MiB free time=2025-08-07T13:47:35.876Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:45783" llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Model llama_model_loader: - kv 3: general.size_label str = 3.6B llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.context_length u32 = 32768 llama_model_loader: - kv 6: llama.embedding_length u32 = 2560 llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240 llama_model_loader: - kv 8: llama.attention.head_count u32 = 32 llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 12: llama.attention.key_length u32 = 128 llama_model_loader: - kv 13: llama.attention.value_length u32 = 128 llama_model_loader: - kv 14: llama.vocab_size u32 = 73448 llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 16: tokenizer.ggml.model str = llama llama_model_loader: - kv 17: tokenizer.ggml.pre str = default llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["<unk>", "<s>", "</s>", "<SEP>", "<C... llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440 llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 30: general.quantization_version u32 = 2 llama_model_loader: - kv 31: general.file_type u32 = 15 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 2.04 GiB (4.85 BPW) load: special tokens cache size = 92 load: token to piece cache size = 0.4342 MB print_info: arch = llama print_info: vocab_only = 0 print_info: n_ctx_train = 32768 print_info: n_embd = 2560 print_info: n_layer = 32 print_info: n_head = 32 print_info: n_head_kv = 2 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_swa_pattern = 1 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 16 print_info: n_embd_k_gqa = 256 print_info: n_embd_v_gqa = 256 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-06 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: f_attn_scale = 0.0e+00 print_info: n_ff = 10240 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 0 print_info: rope scaling = linear print_info: freq_base_train = 10000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 32768 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 8B print_info: model params = 3.61 B print_info: general.name = Model print_info: vocab type = SPM print_info: n_vocab = 73448 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 73440 '<|im_end|>' print_info: EOT token = 73440 '<|im_end|>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 2 '</s>' print_info: LF token = 1099 '<0x0A>' print_info: FIM PRE token = 73445 '<|fim_prefix|>' print_info: FIM SUF token = 73447 '<|fim_suffix|>' print_info: FIM MID token = 73446 '<|fim_middle|>' print_info: EOG token = 73440 '<|im_end|>' print_info: max token length = 48 load_tensors: loading model tensors, this can take a while... (mmap = true) load_tensors: offloading 32 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 33/33 layers to GPU load_tensors: ROCm0 model buffer size = 1985.93 MiB load_tensors: CPU_Mapped model buffer size = 100.87 MiB time=2025-08-07T13:47:36.108Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 4096 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 512 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = 0 llama_context: freq_base = 10000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized llama_context: ROCm_Host output buffer size = 0.29 MiB llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1, padding = 32 llama_kv_cache_unified: ROCm0 KV buffer size = 128.00 MiB llama_kv_cache_unified: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB llama_context: ROCm0 compute buffer size = 290.00 MiB llama_context: ROCm_Host compute buffer size = 13.01 MiB llama_context: graph nodes = 1094 llama_context: graph splits = 2 clip_ctx: CLIP using ROCm0 backend clip_model_loader: model name: clip_model_loader: description: image encoder for MiniCPM-V clip_model_loader: GGUF version: 3 clip_model_loader: alignment: 32 clip_model_loader: n_tensors: 455 clip_model_loader: n_kv: 19 clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=655360, offset=0, shape:[2560, 64, 1, 1], type = f32 clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=50176000, offset=655360, shape:[2560, 4900, 1, 1], type = f32 clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=13107200, offset=50831360, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=5898240, offset=63938560, shape:[1152, 2560, 1, 1], type = f16 clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=13107200, offset=69836800, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=13107200, offset=82944000, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=13107200, offset=96051200, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=10240, offset=109158400, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=10240, offset=109168640, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=10240, offset=109178880, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=13107200, offset=109189120, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=10240, offset=122296320, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=10240, offset=122306560, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=10240, offset=122316800, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=10240, offset=122327040, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=10240, offset=122337280, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=10240, offset=122347520, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=10240, offset=122357760, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=122368000, shape:[14, 14, 3, 1152], type = f16 clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=123722752, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=123727360, shape:[1152, 4900, 1, 1], type = f16 clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=135016960, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=137671168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=137675776, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=140329984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=140334592, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=142988800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=142993408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=145647616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=145652224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=145656832, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=145661440, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=155577856, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=155595072, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=165511488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=165516096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=165520704, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=165525312, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=168179520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=168184128, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=170838336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=170842944, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=173497152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=173501760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=176155968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=176160576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=176165184, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=176169792, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=186086208, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=186103424, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=196019840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=196024448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=196029056, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=196033664, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=198687872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=198692480, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=201346688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=201351296, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=204005504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=204010112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=206664320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=206668928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=206673536, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=206678144, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=216594560, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=216611776, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=226528192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=226532800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=226537408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=226542016, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=229196224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=229200832, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=231855040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=231859648, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=234513856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=234518464, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=237172672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=237177280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=237181888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=237186496, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=247102912, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=247120128, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=257036544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=257041152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=257045760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=257050368, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=259704576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=259709184, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=262363392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=262368000, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=265022208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=265026816, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=267681024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=267685632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=267690240, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=267694848, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=277611264, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=277628480, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=287544896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=287549504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=287554112, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=287558720, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=290212928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=290217536, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=292871744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=292876352, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=295530560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=295535168, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=298189376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=298193984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=298198592, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=298203200, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=308119616, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=308136832, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=318053248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=318057856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=318062464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=318067072, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=320721280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=320725888, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=323380096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=323384704, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=326038912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=326043520, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=328697728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=328702336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=328706944, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=328711552, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=338627968, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=338645184, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=348561600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=348566208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=348570816, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=348575424, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=351229632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=351234240, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=353888448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=353893056, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=356547264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=356551872, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=359206080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=359210688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=359215296, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=359219904, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=369136320, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=369153536, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=379069952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=379074560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=379079168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=379083776, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=381737984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=381742592, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=384396800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=384401408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=387055616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=387060224, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=389714432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=389719040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=389723648, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=389728256, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=399644672, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=399661888, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=409578304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=409582912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=409587520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=409592128, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=412246336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=412250944, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=414905152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=414909760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=417563968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=417568576, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=420222784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=420227392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=420232000, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=420236608, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=430153024, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=430170240, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=440086656, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=440091264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=440095872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=440100480, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=442754688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=442759296, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=445413504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=445418112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=448072320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=448076928, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=450731136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=450735744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=450740352, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=450744960, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=460661376, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=460678592, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=470595008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=470599616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=470604224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=470608832, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=473263040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=473267648, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=475921856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=475926464, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=478580672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=478585280, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=481239488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=481244096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=481248704, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=481253312, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=491169728, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=491186944, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=501103360, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=501107968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=501112576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=501117184, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=503771392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=503776000, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=506430208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=506434816, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=509089024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=509093632, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=511747840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=511752448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=511757056, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=511761664, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=521678080, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=521695296, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=531611712, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=531616320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=531620928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=531625536, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=534279744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=534284352, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=536938560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=536943168, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=539597376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=539601984, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=542256192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=542260800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=542265408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=542270016, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=552186432, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=552203648, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=562120064, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=562124672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=562129280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=562133888, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=564788096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=564792704, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=567446912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=567451520, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=570105728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=570110336, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=572764544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=572769152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=572773760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=572778368, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=582694784, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=582712000, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=592628416, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=592633024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=592637632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=592642240, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=595296448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=595301056, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=597955264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=597959872, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=600614080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=600618688, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=603272896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=603277504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=603282112, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=603286720, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=613203136, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=613220352, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=623136768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=623141376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=623145984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=623150592, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=625804800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=625809408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=628463616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=628468224, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=631122432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=631127040, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=633781248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=633785856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=633790464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=633795072, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=643711488, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=643728704, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=653645120, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=653649728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=653654336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=653658944, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=656313152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=656317760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=658971968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=658976576, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=661630784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=661635392, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=664289600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=664294208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=664298816, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=664303424, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=674219840, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=674237056, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=684153472, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=684158080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=684162688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=684167296, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=686821504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=686826112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=689480320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=689484928, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=692139136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=692143744, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=694797952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=694802560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=694807168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=694811776, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=704728192, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=704745408, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=714661824, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=714666432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=714671040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=714675648, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=717329856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=717334464, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=719988672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=719993280, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=722647488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=722652096, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=725306304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=725310912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=725315520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=725320128, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=735236544, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=735253760, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=745170176, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=745174784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=745179392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=745184000, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=747838208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=747842816, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=750497024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=750501632, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=753155840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=753160448, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=755814656, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=755819264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=755823872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=755828480, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=765744896, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=765762112, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=775678528, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=775683136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=775687744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=775692352, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=778346560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=778351168, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=781005376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=781009984, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=783664192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=783668800, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=786323008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=786327616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=786332224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=786336832, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=796253248, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=796270464, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=806186880, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=806191488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=806196096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=806200704, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=808854912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=808859520, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=811513728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=811518336, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=814172544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=814177152, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=816831360, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=816835968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=816840576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=816845184, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=826761600, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=826778816, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=836695232, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=836699840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=836704448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=836709056, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=839363264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=839367872, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=842022080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=842026688, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=844680896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=844685504, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=847339712, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=847344320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=847348928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=847353536, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=857269952, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=857287168, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=867203584, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=867208192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=867212800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=867217408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=869871616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=869876224, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=872530432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=872535040, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=875189248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=875193856, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=877848064, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=877852672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=877857280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=877861888, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=887778304, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=887795520, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=897711936, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=897716544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=897721152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=897725760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=900379968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=900384576, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=903038784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=903043392, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=905697600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=905702208, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=908356416, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=908361024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=908365632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=908370240, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=918286656, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=918303872, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=928220288, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=928224896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=928229504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=928234112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=930888320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=930892928, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=933547136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=933551744, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=936205952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=936210560, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=938864768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=938869376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=938873984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=938878592, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=948795008, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=948812224, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=958728640, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=958733248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=958737856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=958742464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=958747072, shape:[1152, 1, 1, 1], type = f32 load_hparams: projector: resampler load_hparams: n_embd: 1152 load_hparams: n_head: 16 load_hparams: n_ff: 4304 load_hparams: n_layer: 27 load_hparams: projection_dim: 0 load_hparams: image_size: 448 load_hparams: patch_size: 14 load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 5 load_hparams: proj_scale_factor: 0 load_hparams: n_wa_pattern: 0 load_hparams: ffn_op: gelu load_hparams: model size: 914.34 MiB load_hparams: metadata size: 0.16 MiB load_tensors: loaded 455 tensors from /root/.ollama/models/blobs/sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761 clip.cpp:3782: Unknown minicpmv version Memory critical error by agent node-0 (Agent handle: 0x59ba7d536b40) on address 0x79a845f00000. Reason: Memory in use. SIGABRT: abort PC=0x79aa526d7b2c m=5 sigcode=18446744073709551610 signal arrived during cgo execution goroutine 10 gp=0xc000505180 m=5 mp=0xc000100008 [syscall]: runtime.cgocall(0x59ba7578a080, 0xc00008bc58) runtime/cgocall.go:167 +0x4b fp=0xc00008bc30 sp=0xc00008bbf8 pc=0x59ba74ab98cb github.com/ollama/ollama/llama._Cfunc_clip_model_load(0x79a9f59354f0, 0x1) _cgo_gotypes.go:315 +0x4b fp=0xc00008bc58 sp=0xc00008bc30 pc=0x59ba74e6706b github.com/ollama/ollama/llama.NewClipContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62}) github.com/ollama/ollama/llama/llama.go:470 +0x90 fp=0xc00008bd18 sp=0xc00008bc58 pc=0x59ba74e6cbd0 github.com/ollama/ollama/runner/llamarunner.NewImageContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62}) github.com/ollama/ollama/runner/llamarunner/image.go:35 +0x105 fp=0xc00008bd98 sp=0xc00008bd18 pc=0x59ba74f23e05 github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0004e4360, {0x21, 0x0, 0x1, {0x0, 0x0, 0x0}, 0xc000045940, 0x0}, {0x7ffda9dddcf7, ...}, ...) github.com/ollama/ollama/runner/llamarunner/runner.go:771 +0x248 fp=0xc00008bee0 sp=0xc00008bd98 pc=0x59ba74f28e68 github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0x175 fp=0xc00008bfe0 sp=0xc00008bee0 pc=0x59ba74f2a4d5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008bfe8 sp=0xc00008bfe0 pc=0x59ba74ac4481 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0xb57 goroutine 1 gp=0xc000002380 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000525608 sp=0xc0005255e8 pc=0x59ba74abcd4e runtime.netpollblock(0xc000525688?, 0x74a55b46?, 0xba?) runtime/netpoll.go:575 +0xf7 fp=0xc000525640 sp=0xc000525608 pc=0x59ba74a81837 internal/poll.runtime_pollWait(0x79aa5246aeb0, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000525660 sp=0xc000525640 pc=0x59ba74abbf65 internal/poll.(*pollDesc).wait(0xc0001cdb80?, 0x59ba74a64546?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000525688 sp=0xc000525660 pc=0x59ba74b433a7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc0001cdb80) internal/poll/fd_unix.go:620 +0x295 fp=0xc000525730 sp=0xc000525688 pc=0x59ba74b48775 net.(*netFD).accept(0xc0001cdb80) net/fd_unix.go:172 +0x29 fp=0xc0005257e8 sp=0xc000525730 pc=0x59ba74bbad89 net.(*TCPListener).accept(0xc0002e4340) net/tcpsock_posix.go:159 +0x1b fp=0xc000525838 sp=0xc0005257e8 pc=0x59ba74bd073b net.(*TCPListener).Accept(0xc0002e4340) net/tcpsock.go:380 +0x30 fp=0xc000525868 sp=0xc000525838 pc=0x59ba74bcf5f0 net/http.(*onceCloseListener).Accept(0xc00053c000?) <autogenerated>:1 +0x24 fp=0xc000525880 sp=0xc000525868 pc=0x59ba74de6d44 net/http.(*Server).Serve(0xc00051d500, {0x59ba75e302e8, 0xc0002e4340}) net/http/server.go:3424 +0x30c fp=0xc0005259b0 sp=0xc000525880 pc=0x59ba74dbe60c github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034140, 0x10, 0x10}) github.com/ollama/ollama/runner/llamarunner/runner.go:875 +0x100a fp=0xc000525d08 sp=0xc0005259b0 pc=0x59ba74f2a06a github.com/ollama/ollama/runner.Execute({0xc000034130?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000525d30 sp=0xc000525d08 pc=0x59ba74fb3934 github.com/ollama/ollama/cmd.NewCLI.func2(0xc00051d000?, {0x59ba7597307e?, 0x4?, 0x59ba75973082?}) github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000525d58 sp=0xc000525d30 pc=0x59ba75718685 github.com/spf13/cobra.(*Command).execute(0xc0004e6f08, {0xc00051d200, 0x10, 0x10}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000525e78 sp=0xc000525d58 pc=0x59ba74c343dc github.com/spf13/cobra.(*Command).ExecuteC(0xc000494f08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000525f30 sp=0xc000525e78 pc=0x59ba74c34c25 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000525f50 sp=0xc000525f30 pc=0x59ba7571916d runtime.main() runtime/proc.go:283 +0x29d fp=0xc000525fe0 sp=0xc000525f50 pc=0x59ba74a88ebd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000525fe8 sp=0xc000525fe0 pc=0x59ba74ac4481 goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000072fa8 sp=0xc000072f88 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000072fe0 sp=0xc000072fa8 pc=0x59ba74a891f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x59ba74ac4481 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000073780 sp=0xc000073760 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00007e000) runtime/mgcsweep.go:316 +0xdf fp=0xc0000737c8 sp=0xc000073780 pc=0x59ba74a7399f runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x59ba74a67d85 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x59ba74ac4481 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x59ba75b35158?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000073f78 sp=0xc000073f58 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x59ba766c79a0) runtime/mgcscavenge.go:425 +0x49 fp=0xc000073fa8 sp=0xc000073f78 pc=0x59ba74a713e9 runtime.bgscavenge(0xc00007e000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000073fc8 sp=0xc000073fa8 pc=0x59ba74a71979 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x59ba74a67d25 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x59ba74ac4481 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000072688?) runtime/proc.go:435 +0xce fp=0xc000072630 sp=0xc000072610 pc=0x59ba74abcd4e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc0000727e0 sp=0xc000072630 pc=0x59ba74a66d47 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x59ba74ac4481 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]: runtime.gopark(0xc000225860?, 0xc000590018?, 0x60?, 0x47?, 0x59ba74ba19c8?) runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x59ba74abcd4e runtime.chanrecv(0xc0000aa310, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x59ba74a58725 runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x59ba74a582b2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x59ba74a6af2f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x59ba74ac4481 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0001d1180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006ef38 sp=0xc00006ef18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006efc8 sp=0xc00006ef38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006efe0 sp=0xc00006efc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0001d1340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000102700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006f738 sp=0xc00006f718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006f7c8 sp=0xc00006f738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0001d1500 m=nil [GC worker (idle)]: runtime.gopark(0x508351928f82?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000075f38 sp=0xc000075f18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc000075fc8 sp=0xc000075f38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000075fe0 sp=0xc000075fc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000075fe8 sp=0xc000075fe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000504700 m=nil [GC worker (idle)]: runtime.gopark(0x508351921eb8?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc0005048c0 m=nil [GC worker (idle)]: runtime.gopark(0x508351921f94?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc000504a80 m=nil [GC worker (idle)]: runtime.gopark(0x508351923a9f?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 21 gp=0xc0001028c0 m=nil [GC worker (idle)]: runtime.gopark(0x508351928bf2?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006ff38 sp=0xc00006ff18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006ffc8 sp=0xc00006ff38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006ffe0 sp=0xc00006ffc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 11 gp=0xc000505340 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0x0?, 0x0?, 0x60?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050ce20 sp=0xc00050ce00 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.semacquire1(0xc0004e4368, 0x0, 0x1, 0x0, 0x18) runtime/sema.go:188 +0x229 fp=0xc00050ce88 sp=0xc00050ce20 pc=0x59ba74a9c489 sync.runtime_SemacquireWaitGroup(0x0?) runtime/sema.go:110 +0x25 fp=0xc00050cec0 sp=0xc00050ce88 pc=0x59ba74abe765 sync.(*WaitGroup).Wait(0x0?) sync/waitgroup.go:118 +0x48 fp=0xc00050cee8 sp=0xc00050cec0 pc=0x59ba74acfdc8 github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0004e4360, {0x59ba75e32790, 0xc0000f4af0}) github.com/ollama/ollama/runner/llamarunner/runner.go:314 +0x47 fp=0xc00050cfb8 sp=0xc00050cee8 pc=0x59ba74f259e7 github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2() github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0x28 fp=0xc00050cfe0 sp=0xc00050cfb8 pc=0x59ba74f2a328 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050cfe8 sp=0xc00050cfe0 pc=0x59ba74ac4481 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0xc37 goroutine 39 gp=0xc000102a80 m=nil [IO wait]: runtime.gopark(0x59ba74b469a5?, 0xc000474000?, 0x40?, 0x9a?, 0xb?) runtime/proc.go:435 +0xce fp=0xc000129948 sp=0xc000129928 pc=0x59ba74abcd4e runtime.netpollblock(0x59ba74ae00b8?, 0x74a55b46?, 0xba?) runtime/netpoll.go:575 +0xf7 fp=0xc000129980 sp=0xc000129948 pc=0x59ba74a81837 internal/poll.runtime_pollWait(0x79aa5246ad98, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0001299a0 sp=0xc000129980 pc=0x59ba74abbf65 internal/poll.(*pollDesc).wait(0xc000474000?, 0xc0004fe000?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001299c8 sp=0xc0001299a0 pc=0x59ba74b433a7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc000474000, {0xc0004fe000, 0x1000, 0x1000}) internal/poll/fd_unix.go:165 +0x27a fp=0xc000129a60 sp=0xc0001299c8 pc=0x59ba74b4469a net.(*netFD).Read(0xc000474000, {0xc0004fe000?, 0xc000129ad0?, 0x59ba74b43865?}) net/fd_posix.go:55 +0x25 fp=0xc000129aa8 sp=0xc000129a60 pc=0x59ba74bb8de5 net.(*conn).Read(0xc00053a000, {0xc0004fe000?, 0x0?, 0x0?}) net/net.go:194 +0x45 fp=0xc000129af0 sp=0xc000129aa8 pc=0x59ba74bc71a5 net/http.(*connReader).Read(0xc0004f8090, {0xc0004fe000, 0x1000, 0x1000}) net/http/server.go:798 +0x159 fp=0xc000129b40 sp=0xc000129af0 pc=0x59ba74db34b9 bufio.(*Reader).fill(0xc000110660) bufio/bufio.go:113 +0x103 fp=0xc000129b78 sp=0xc000129b40 pc=0x59ba74bde943 bufio.(*Reader).Peek(0xc000110660, 0x4) bufio/bufio.go:152 +0x53 fp=0xc000129b98 sp=0xc000129b78 pc=0x59ba74bdea73 net/http.(*conn).serve(0xc00053c000, {0x59ba75e32758, 0xc0004f8030}) net/http/server.go:2137 +0x785 fp=0xc000129fb8 sp=0xc000129b98 pc=0x59ba74db92a5 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000129fe0 sp=0xc000129fb8 pc=0x59ba74dbea08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000129fe8 sp=0xc000129fe0 pc=0x59ba74ac4481 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 rax 0x0 rbx 0x33 rcx 0x79aa526d7b2c rdx 0x6 rdi 0x33 rsi 0x33 rbp 0x79aa0a2fb720 rsp 0x79aa0a2fb6e0 r8 0x78 r9 0x0 r10 0x8 r11 0x246 r12 0x6 r13 0x0 r14 0x16 r15 0x0 rip 0x79aa526d7b2c rflags 0x246 cs 0x33 fs 0x0 gs 0x0 SIGABRT: abort PC=0x79aa526d7b2c m=5 sigcode=18446744073709551610 signal arrived during cgo execution goroutine 10 gp=0xc000505180 m=5 mp=0xc000100008 [syscall]: runtime.cgocall(0x59ba7578a080, 0xc00008bc58) runtime/cgocall.go:167 +0x4b fp=0xc00008bc30 sp=0xc00008bbf8 pc=0x59ba74ab98cb github.com/ollama/ollama/llama._Cfunc_clip_model_load(0x79a9f59354f0, 0x1) _cgo_gotypes.go:315 +0x4b fp=0xc00008bc58 sp=0xc00008bc30 pc=0x59ba74e6706b github.com/ollama/ollama/llama.NewClipContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62}) github.com/ollama/ollama/llama/llama.go:470 +0x90 fp=0xc00008bd18 sp=0xc00008bc58 pc=0x59ba74e6cbd0 github.com/ollama/ollama/runner/llamarunner.NewImageContext(0xc0003ae010, {0x7ffda9ddddaf, 0x62}) github.com/ollama/ollama/runner/llamarunner/image.go:35 +0x105 fp=0xc00008bd98 sp=0xc00008bd18 pc=0x59ba74f23e05 github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0004e4360, {0x21, 0x0, 0x1, {0x0, 0x0, 0x0}, 0xc000045940, 0x0}, {0x7ffda9dddcf7, ...}, ...) github.com/ollama/ollama/runner/llamarunner/runner.go:771 +0x248 fp=0xc00008bee0 sp=0xc00008bd98 pc=0x59ba74f28e68 github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0x175 fp=0xc00008bfe0 sp=0xc00008bee0 pc=0x59ba74f2a4d5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00008bfe8 sp=0xc00008bfe0 pc=0x59ba74ac4481 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0xb57 goroutine 1 gp=0xc000002380 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000525608 sp=0xc0005255e8 pc=0x59ba74abcd4e runtime.netpollblock(0xc000525688?, 0x74a55b46?, 0xba?) runtime/netpoll.go:575 +0xf7 fp=0xc000525640 sp=0xc000525608 pc=0x59ba74a81837 internal/poll.runtime_pollWait(0x79aa5246aeb0, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000525660 sp=0xc000525640 pc=0x59ba74abbf65 internal/poll.(*pollDesc).wait(0xc0001cdb80?, 0x59ba74a64546?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000525688 sp=0xc000525660 pc=0x59ba74b433a7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc0001cdb80) internal/poll/fd_unix.go:620 +0x295 fp=0xc000525730 sp=0xc000525688 pc=0x59ba74b48775 net.(*netFD).accept(0xc0001cdb80) net/fd_unix.go:172 +0x29 fp=0xc0005257e8 sp=0xc000525730 pc=0x59ba74bbad89 net.(*TCPListener).accept(0xc0002e4340) net/tcpsock_posix.go:159 +0x1b fp=0xc000525838 sp=0xc0005257e8 pc=0x59ba74bd073b net.(*TCPListener).Accept(0xc0002e4340) net/tcpsock.go:380 +0x30 fp=0xc000525868 sp=0xc000525838 pc=0x59ba74bcf5f0 net/http.(*onceCloseListener).Accept(0xc00053c000?) <autogenerated>:1 +0x24 fp=0xc000525880 sp=0xc000525868 pc=0x59ba74de6d44 net/http.(*Server).Serve(0xc00051d500, {0x59ba75e302e8, 0xc0002e4340}) net/http/server.go:3424 +0x30c fp=0xc0005259b0 sp=0xc000525880 pc=0x59ba74dbe60c github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034140, 0x10, 0x10}) github.com/ollama/ollama/runner/llamarunner/runner.go:875 +0x100a fp=0xc000525d08 sp=0xc0005259b0 pc=0x59ba74f2a06a github.com/ollama/ollama/runner.Execute({0xc000034130?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000525d30 sp=0xc000525d08 pc=0x59ba74fb3934 github.com/ollama/ollama/cmd.NewCLI.func2(0xc00051d000?, {0x59ba7597307e?, 0x4?, 0x59ba75973082?}) github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000525d58 sp=0xc000525d30 pc=0x59ba75718685 github.com/spf13/cobra.(*Command).execute(0xc0004e6f08, {0xc00051d200, 0x10, 0x10}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000525e78 sp=0xc000525d58 pc=0x59ba74c343dc github.com/spf13/cobra.(*Command).ExecuteC(0xc000494f08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000525f30 sp=0xc000525e78 pc=0x59ba74c34c25 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000525f50 sp=0xc000525f30 pc=0x59ba7571916d runtime.main() runtime/proc.go:283 +0x29d fp=0xc000525fe0 sp=0xc000525f50 pc=0x59ba74a88ebd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000525fe8 sp=0xc000525fe0 pc=0x59ba74ac4481 goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000072fa8 sp=0xc000072f88 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc000072fe0 sp=0xc000072fa8 pc=0x59ba74a891f8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x59ba74ac4481 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000073780 sp=0xc000073760 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc00007e000) runtime/mgcsweep.go:316 +0xdf fp=0xc0000737c8 sp=0xc000073780 pc=0x59ba74a7399f runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x59ba74a67d85 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x59ba74ac4481 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x59ba75b35158?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000073f78 sp=0xc000073f58 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x59ba766c79a0) runtime/mgcscavenge.go:425 +0x49 fp=0xc000073fa8 sp=0xc000073f78 pc=0x59ba74a713e9 runtime.bgscavenge(0xc00007e000) runtime/mgcscavenge.go:658 +0x59 fp=0xc000073fc8 sp=0xc000073fa8 pc=0x59ba74a71979 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x59ba74a67d25 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x59ba74ac4481 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000072688?) runtime/proc.go:435 +0xce fp=0xc000072630 sp=0xc000072610 pc=0x59ba74abcd4e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc0000727e0 sp=0xc000072630 pc=0x59ba74a66d47 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x59ba74ac4481 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]: runtime.gopark(0xc000225860?, 0xc000590018?, 0x60?, 0x47?, 0x59ba74ba19c8?) runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x59ba74abcd4e runtime.chanrecv(0xc0000aa310, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x59ba74a58725 runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x59ba74a582b2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x59ba74a6af2f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x59ba74ac4481 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0001d1180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006e738 sp=0xc00006e718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006e7c8 sp=0xc00006e738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006e7e0 sp=0xc00006e7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006e7e8 sp=0xc00006e7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006ef38 sp=0xc00006ef18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006efc8 sp=0xc00006ef38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006efe0 sp=0xc00006efc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006efe8 sp=0xc00006efe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0001d1340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000102700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006f738 sp=0xc00006f718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006f7c8 sp=0xc00006f738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006f7e0 sp=0xc00006f7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006f7e8 sp=0xc00006f7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0001d1500 m=nil [GC worker (idle)]: runtime.gopark(0x508351928f82?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000075f38 sp=0xc000075f18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc000075fc8 sp=0xc000075f38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000075fe0 sp=0xc000075fc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000075fe8 sp=0xc000075fe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000504700 m=nil [GC worker (idle)]: runtime.gopark(0x508351921eb8?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc0005048c0 m=nil [GC worker (idle)]: runtime.gopark(0x508351921f94?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc000504a80 m=nil [GC worker (idle)]: runtime.gopark(0x508351923a9f?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 21 gp=0xc0001028c0 m=nil [GC worker (idle)]: runtime.gopark(0x508351928bf2?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00006ff38 sp=0xc00006ff18 pc=0x59ba74abcd4e runtime.gcBgMarkWorker(0xc0000ab730) runtime/mgc.go:1423 +0xe9 fp=0xc00006ffc8 sp=0xc00006ff38 pc=0x59ba74a6a249 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00006ffe0 sp=0xc00006ffc8 pc=0x59ba74a6a125 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00006ffe8 sp=0xc00006ffe0 pc=0x59ba74ac4481 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 11 gp=0xc000505340 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0x0?, 0x0?, 0x60?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00050ce20 sp=0xc00050ce00 pc=0x59ba74abcd4e runtime.goparkunlock(...) runtime/proc.go:441 runtime.semacquire1(0xc0004e4368, 0x0, 0x1, 0x0, 0x18) runtime/sema.go:188 +0x229 fp=0xc00050ce88 sp=0xc00050ce20 pc=0x59ba74a9c489 sync.runtime_SemacquireWaitGroup(0x0?) runtime/sema.go:110 +0x25 fp=0xc00050cec0 sp=0xc00050ce88 pc=0x59ba74abe765 sync.(*WaitGroup).Wait(0x0?) sync/waitgroup.go:118 +0x48 fp=0xc00050cee8 sp=0xc00050cec0 pc=0x59ba74acfdc8 github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0004e4360, {0x59ba75e32790, 0xc0000f4af0}) github.com/ollama/ollama/runner/llamarunner/runner.go:314 +0x47 fp=0xc00050cfb8 sp=0xc00050cee8 pc=0x59ba74f259e7 github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2() github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0x28 fp=0xc00050cfe0 sp=0xc00050cfb8 pc=0x59ba74f2a328 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00050cfe8 sp=0xc00050cfe0 pc=0x59ba74ac4481 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0xc37 goroutine 39 gp=0xc000102a80 m=nil [IO wait]: runtime.gopark(0x59ba74b469a5?, 0xc000474000?, 0x40?, 0x9a?, 0xb?) runtime/proc.go:435 +0xce fp=0xc000129948 sp=0xc000129928 pc=0x59ba74abcd4e runtime.netpollblock(0x59ba74ae00b8?, 0x74a55b46?, 0xba?) runtime/netpoll.go:575 +0xf7 fp=0xc000129980 sp=0xc000129948 pc=0x59ba74a81837 internal/poll.runtime_pollWait(0x79aa5246ad98, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0001299a0 sp=0xc000129980 pc=0x59ba74abbf65 internal/poll.(*pollDesc).wait(0xc000474000?, 0xc0004fe000?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001299c8 sp=0xc0001299a0 pc=0x59ba74b433a7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc000474000, {0xc0004fe000, 0x1000, 0x1000}) internal/poll/fd_unix.go:165 +0x27a fp=0xc000129a60 sp=0xc0001299c8 pc=0x59ba74b4469a net.(*netFD).Read(0xc000474000, {0xc0004fe000?, 0xc000129ad0?, 0x59ba74b43865?}) net/fd_posix.go:55 +0x25 fp=0xc000129aa8 sp=0xc000129a60 pc=0x59ba74bb8de5 net.(*conn).Read(0xc00053a000, {0xc0004fe000?, 0x0?, 0x0?}) net/net.go:194 +0x45 fp=0xc000129af0 sp=0xc000129aa8 pc=0x59ba74bc71a5 net/http.(*connReader).Read(0xc0004f8090, {0xc0004fe000, 0x1000, 0x1000}) net/http/server.go:798 +0x159 fp=0xc000129b40 sp=0xc000129af0 pc=0x59ba74db34b9 bufio.(*Reader).fill(0xc000110660) bufio/bufio.go:113 +0x103 fp=0xc000129b78 sp=0xc000129b40 pc=0x59ba74bde943 bufio.(*Reader).Peek(0xc000110660, 0x4) bufio/bufio.go:152 +0x53 fp=0xc000129b98 sp=0xc000129b78 pc=0x59ba74bdea73 net/http.(*conn).serve(0xc00053c000, {0x59ba75e32758, 0xc0004f8030}) net/http/server.go:2137 +0x785 fp=0xc000129fb8 sp=0xc000129b98 pc=0x59ba74db92a5 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000129fe0 sp=0xc000129fb8 pc=0x59ba74dbea08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000129fe8 sp=0xc000129fe0 pc=0x59ba74ac4481 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 rax 0x0 rbx 0x2b rcx 0x79aa526d7b2c rdx 0x6 rdi 0x27 rsi 0x2b rbp 0x79aa0a2fb9a0 rsp 0x79aa0a2fb960 r8 0x0 r9 0x0 r10 0x8 r11 0x246 r12 0x6 r13 0xec6 r14 0x16 r15 0xc0000da000 rip 0x79aa526d7b2c rflags 0x246 cs 0x33 fs 0x0 gs 0x0 time=2025-08-07T13:47:36.860Z level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 2" [GIN] 2025/08/07 - 13:47:36 | 500 | 2.32287378s | 127.0.0.1 | POST "/api/generate" time=2025-08-07T13:47:41.861Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.000299103 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=39 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b time=2025-08-07T13:47:42.111Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.25111742 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=39 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b time=2025-08-07T13:47:42.361Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.50081186 runner.size="3.7 GiB" runner.vram="3.7 GiB" runner.parallel=1 runner.pid=39 runner.model=/root/.ollama/models/blobs/sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
GiteaMirror commented 2026-05-04 19:37:27 -05:00
Author
Owner
Copy Link

@sunskyx commented on GitHub (Aug 7, 2025):

I run openbmb/MiniCPM-V-4-gguf:Q4_K_M using Docker, on Ubuntu 24.04.2 + 7900XTX.

<!-- gh-comment-id:3164293688 --> @sunskyx commented on GitHub (Aug 7, 2025): I run openbmb/MiniCPM-V-4-gguf:Q4_K_M using Docker, on Ubuntu 24.04.2 + 7900XTX.
GiteaMirror commented 2026-05-04 19:37:32 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 7, 2025):

clip.cpp:3782: Unknown minicpmv version
Memory critical error by agent node-0 (Agent handle: 0x59ba7d536b40) on address 0x79a845f00000. Reason: Memory in use.

#11730

<!-- gh-comment-id:3164368958 --> @rick-github commented on GitHub (Aug 7, 2025): ``` clip.cpp:3782: Unknown minicpmv version Memory critical error by agent node-0 (Agent handle: 0x59ba7d536b40) on address 0x79a845f00000. Reason: Memory in use. ``` #11730
GiteaMirror commented 2026-05-04 19:37:35 -05:00
Author
Owner
Copy Link

@Alias4D commented on GitHub (Aug 11, 2025):

time=2025-08-11T21:15:41.124+03:00 level=INFO source=routes.go:1304 msg="server config" env="map[CUDA_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_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\AI\Ollama 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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-08-11T21:15:41.132+03:00 level=INFO source=images.go:477 msg="total blobs: 132"
time=2025-08-11T21:15:41.134+03:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2025-08-11T21:15:41.137+03:00 level=INFO source=routes.go:1357 msg="Listening on [::]:11434 (version 0.11.4)"
time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=10 efficiency=4 threads=16
time=2025-08-11T21:15:41.844+03:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-9587ec6b-451e-6399-d84f-22272b7cc6fd library=cuda compute=8.6 driver=12.8 name="NVIDIA GeForce RTX 3050 Laptop GPU" overhead="660.6 MiB"
time=2025-08-11T21:15:41.846+03:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-9587ec6b-451e-6399-d84f-22272b7cc6fd library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA GeForce RTX 3050 Laptop GPU" total="4.0 GiB" available="3.2 GiB"
time=2025-08-11T21:15:41.846+03:00 level=INFO source=routes.go:1398 msg="entering low vram mode" "total vram"="4.0 GiB" threshold="20.0 GiB"
[GIN] 2025/08/11 - 21:15:44 | 404 | 5.7397ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/11 - 21:15:44 | 200 | 6.2476ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/08/11 - 21:15:45 | 404 | 3.3559ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/11 - 21:15:47 | 404 | 5.8923ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/11 - 21:15:51 | 404 | 2.4693ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/11 - 21:15:57 | 200 | 30.0835ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/11 - 21:16:02 | 200 | 6.8315ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/08/11 - 21:16:02 | 200 | 21.8138ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/08/11 - 21:16:02 | 200 | 19.5197ms | 127.0.0.1 | POST "/api/show"
time=2025-08-11T21:16:02.157+03:00 level=INFO source=server.go:135 msg="system memory" total="15.7 GiB" free="7.9 GiB" free_swap="12.2 GiB"
time=2025-08-11T21:16:02.158+03:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=33 layers.offload=25 layers.split="" memory.available="[3.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.8 GiB" memory.required.partial="3.2 GiB" memory.required.kv="128.0 MiB" memory.required.allocations="[3.2 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="147.1 MiB" memory.graph.full="284.0 MiB" memory.graph.partial="300.5 MiB" projector.weights="914.3 MiB" projector.graph="0 B"
llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Model
llama_model_loader: - kv 3: general.size_label str = 3.6B
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.context_length u32 = 32768
llama_model_loader: - kv 6: llama.embedding_length u32 = 2560
llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240
llama_model_loader: - kv 8: llama.attention.head_count u32 = 32
llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2
llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 12: llama.attention.key_length u32 = 128
llama_model_loader: - kv 13: llama.attention.value_length u32 = 128
llama_model_loader: - kv 14: llama.vocab_size u32 = 73448
llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 16: tokenizer.ggml.model str = llama
llama_model_loader: - kv 17: tokenizer.ggml.pre str = default
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["", "", "", "", "<C...
llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440
llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 30: general.quantization_version u32 = 2
llama_model_loader: - kv 31: general.file_type u32 = 15
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 2.04 GiB (4.85 BPW)
load: special tokens cache size = 92
load: token to piece cache size = 0.4342 MB
print_info: arch = llama
print_info: vocab_only = 1
print_info: model type = ?B
print_info: model params = 3.61 B
print_info: general.name = Model
print_info: vocab type = SPM
print_info: n_vocab = 73448
print_info: n_merges = 0
print_info: BOS token = 1 ''
print_info: EOS token = 73440 '<|im_end|>'
print_info: EOT token = 73440 '<|im_end|>'
print_info: UNK token = 0 ''
print_info: PAD token = 2 ''
print_info: LF token = 1099 '<0x0A>'
print_info: FIM PRE token = 73445 '<|fim_prefix|>'
print_info: FIM SUF token = 73447 '<|fim_suffix|>'
print_info: FIM MID token = 73446 '<|fim_middle|>'
print_info: EOG token = 73440 '<|im_end|>'
print_info: max token length = 48
llama_model_load: vocab only - skipping tensors
time=2025-08-11T21:16:02.232+03:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\Users\AL-NABAA\AppData\Local\Programs\Ollama\ollama.exe runner --model E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b --ctx-size 4096 --batch-size 512 --n-gpu-layers 25 --threads 6 --no-mmap --parallel 1 --mmproj E:\AI\Ollama\blobs\sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761 --port 64933"
time=2025-08-11T21:16:02.237+03:00 level=INFO source=sched.go:481 msg="loaded runners" count=1
time=2025-08-11T21:16:02.237+03:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-11T21:16:02.240+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-08-11T21:16:02.264+03:00 level=INFO source=runner.go:815 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3050 Laptop GPU, compute capability 8.6, VMM: yes
load_backend: loaded CUDA backend from C:\Users\AL-NABAA\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\AL-NABAA\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-08-11T21:16:03.070+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-08-11T21:16:03.072+03:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:64933"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3050 Laptop GPU) - 3303 MiB free
llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Model
llama_model_loader: - kv 3: general.size_label str = 3.6B
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.context_length u32 = 32768
llama_model_loader: - kv 6: llama.embedding_length u32 = 2560
llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240
llama_model_loader: - kv 8: llama.attention.head_count u32 = 32
llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2
llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 12: llama.attention.key_length u32 = 128
llama_model_loader: - kv 13: llama.attention.value_length u32 = 128
llama_model_loader: - kv 14: llama.vocab_size u32 = 73448
llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 16: tokenizer.ggml.model str = llama
llama_model_loader: - kv 17: tokenizer.ggml.pre str = default
llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["", "", "", "", "<C...
llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440
llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 30: general.quantization_version u32 = 2
llama_model_loader: - kv 31: general.file_type u32 = 15
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 2.04 GiB (4.85 BPW)
load: special tokens cache size = 92
load: token to piece cache size = 0.4342 MB
print_info: arch = llama
print_info: vocab_only = 0
print_info: n_ctx_train = 32768
print_info: n_embd = 2560
print_info: n_layer = 32
print_info: n_head = 32
print_info: n_head_kv = 2
print_info: n_rot = 128
print_info: n_swa = 0
print_info: n_swa_pattern = 1
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 16
print_info: n_embd_k_gqa = 256
print_info: n_embd_v_gqa = 256
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 10240
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 0
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 32768
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 8B
print_info: model params = 3.61 B
print_info: general.name = Model
print_info: vocab type = SPM
print_info: n_vocab = 73448
print_info: n_merges = 0
print_info: BOS token = 1 ''
print_info: EOS token = 73440 '<|im_end|>'
print_info: EOT token = 73440 '<|im_end|>'
print_info: UNK token = 0 ''
print_info: PAD token = 2 ''
print_info: LF token = 1099 '<0x0A>'
print_info: FIM PRE token = 73445 '<|fim_prefix|>'
print_info: FIM SUF token = 73447 '<|fim_suffix|>'
print_info: FIM MID token = 73446 '<|fim_middle|>'
print_info: EOG token = 73440 '<|im_end|>'
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = false)
time=2025-08-11T21:16:03.244+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
load_tensors: offloading 25 repeating layers to GPU
load_tensors: offloaded 25/33 layers to GPU
load_tensors: CUDA_Host model buffer size = 559.26 MiB
load_tensors: CUDA0 model buffer size = 1426.67 MiB
load_tensors: CPU model buffer size = 100.87 MiB
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 512
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: freq_base = 10000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 0.29 MiB
llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1, padding = 32
llama_kv_cache_unified: CUDA0 KV buffer size = 100.00 MiB
llama_kv_cache_unified: CPU KV buffer size = 28.00 MiB
llama_kv_cache_unified: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB
llama_context: CUDA0 compute buffer size = 298.25 MiB
llama_context: CUDA_Host compute buffer size = 13.01 MiB
llama_context: graph nodes = 1094
llama_context: graph splits = 81 (with bs=512), 3 (with bs=1)
clip_ctx: CLIP using CUDA0 backend
clip_model_loader: model name:
clip_model_loader: description: image encoder for MiniCPM-V
clip_model_loader: GGUF version: 3
clip_model_loader: alignment: 32
clip_model_loader: n_tensors: 455
clip_model_loader: n_kv: 19

clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=655360, offset=0, shape:[2560, 64, 1, 1], type = f32
clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=50176000, offset=655360, shape:[2560, 4900, 1, 1], type = f32
clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=13107200, offset=50831360, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=5898240, offset=63938560, shape:[1152, 2560, 1, 1], type = f16
clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=13107200, offset=69836800, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=13107200, offset=82944000, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=13107200, offset=96051200, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=10240, offset=109158400, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=10240, offset=109168640, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=10240, offset=109178880, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=13107200, offset=109189120, shape:[2560, 2560, 1, 1], type = f16
clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=10240, offset=122296320, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=10240, offset=122306560, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=10240, offset=122316800, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=10240, offset=122327040, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=10240, offset=122337280, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=10240, offset=122347520, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=10240, offset=122357760, shape:[2560, 1, 1, 1], type = f32
clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=122368000, shape:[14, 14, 3, 1152], type = f16
clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=123722752, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=123727360, shape:[1152, 4900, 1, 1], type = f16
clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=135016960, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=137671168, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=137675776, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=140329984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=140334592, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=142988800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=142993408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=145647616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=145652224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=145656832, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=145661440, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=155577856, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=155595072, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=165511488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=165516096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=165520704, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=165525312, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=168179520, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=168184128, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=170838336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=170842944, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=173497152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=173501760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=176155968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=176160576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=176165184, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=176169792, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=186086208, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=186103424, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=196019840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=196024448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=196029056, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=196033664, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=198687872, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=198692480, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=201346688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=201351296, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=204005504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=204010112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=206664320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=206668928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=206673536, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=206678144, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=216594560, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=216611776, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=226528192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=226532800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=226537408, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=226542016, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=229196224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=229200832, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=231855040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=231859648, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=234513856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=234518464, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=237172672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=237177280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=237181888, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=237186496, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=247102912, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=247120128, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=257036544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=257041152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=257045760, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=257050368, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=259704576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=259709184, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=262363392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=262368000, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=265022208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=265026816, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=267681024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=267685632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=267690240, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=267694848, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=277611264, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=277628480, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=287544896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=287549504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=287554112, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=287558720, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=290212928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=290217536, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=292871744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=292876352, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=295530560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=295535168, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=298189376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=298193984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=298198592, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=298203200, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=308119616, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=308136832, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=318053248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=318057856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=318062464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=318067072, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=320721280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=320725888, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=323380096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=323384704, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=326038912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=326043520, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=328697728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=328702336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=328706944, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=328711552, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=338627968, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=338645184, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=348561600, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=348566208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=348570816, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=348575424, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=351229632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=351234240, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=353888448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=353893056, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=356547264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=356551872, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=359206080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=359210688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=359215296, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=359219904, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=369136320, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=369153536, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=379069952, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=379074560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=379079168, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=379083776, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=381737984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=381742592, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=384396800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=384401408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=387055616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=387060224, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=389714432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=389719040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=389723648, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=389728256, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=399644672, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=399661888, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=409578304, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=409582912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=409587520, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=409592128, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=412246336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=412250944, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=414905152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=414909760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=417563968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=417568576, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=420222784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=420227392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=420232000, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=420236608, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=430153024, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=430170240, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=440086656, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=440091264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=440095872, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=440100480, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=442754688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=442759296, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=445413504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=445418112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=448072320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=448076928, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=450731136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=450735744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=450740352, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=450744960, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=460661376, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=460678592, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=470595008, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=470599616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=470604224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=470608832, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=473263040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=473267648, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=475921856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=475926464, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=478580672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=478585280, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=481239488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=481244096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=481248704, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=481253312, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=491169728, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=491186944, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=501103360, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=501107968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=501112576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=501117184, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=503771392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=503776000, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=506430208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=506434816, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=509089024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=509093632, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=511747840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=511752448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=511757056, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=511761664, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=521678080, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=521695296, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=531611712, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=531616320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=531620928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=531625536, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=534279744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=534284352, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=536938560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=536943168, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=539597376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=539601984, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=542256192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=542260800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=542265408, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=542270016, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=552186432, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=552203648, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=562120064, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=562124672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=562129280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=562133888, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=564788096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=564792704, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=567446912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=567451520, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=570105728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=570110336, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=572764544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=572769152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=572773760, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=572778368, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=582694784, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=582712000, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=592628416, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=592633024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=592637632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=592642240, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=595296448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=595301056, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=597955264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=597959872, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=600614080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=600618688, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=603272896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=603277504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=603282112, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=603286720, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=613203136, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=613220352, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=623136768, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=623141376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=623145984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=623150592, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=625804800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=625809408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=628463616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=628468224, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=631122432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=631127040, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=633781248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=633785856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=633790464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=633795072, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=643711488, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=643728704, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=653645120, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=653649728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=653654336, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=653658944, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=656313152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=656317760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=658971968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=658976576, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=661630784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=661635392, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=664289600, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=664294208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=664298816, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=664303424, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=674219840, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=674237056, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=684153472, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=684158080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=684162688, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=684167296, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=686821504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=686826112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=689480320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=689484928, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=692139136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=692143744, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=694797952, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=694802560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=694807168, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=694811776, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=704728192, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=704745408, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=714661824, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=714666432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=714671040, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=714675648, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=717329856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=717334464, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=719988672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=719993280, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=722647488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=722652096, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=725306304, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=725310912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=725315520, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=725320128, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=735236544, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=735253760, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=745170176, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=745174784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=745179392, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=745184000, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=747838208, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=747842816, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=750497024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=750501632, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=753155840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=753160448, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=755814656, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=755819264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=755823872, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=755828480, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=765744896, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=765762112, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=775678528, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=775683136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=775687744, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=775692352, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=778346560, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=778351168, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=781005376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=781009984, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=783664192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=783668800, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=786323008, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=786327616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=786332224, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=786336832, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=796253248, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=796270464, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=806186880, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=806191488, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=806196096, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=806200704, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=808854912, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=808859520, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=811513728, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=811518336, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=814172544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=814177152, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=816831360, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=816835968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=816840576, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=816845184, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=826761600, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=826778816, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=836695232, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=836699840, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=836704448, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=836709056, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=839363264, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=839367872, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=842022080, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=842026688, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=844680896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=844685504, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=847339712, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=847344320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=847348928, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=847353536, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=857269952, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=857287168, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=867203584, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=867208192, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=867212800, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=867217408, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=869871616, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=869876224, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=872530432, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=872535040, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=875189248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=875193856, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=877848064, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=877852672, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=877857280, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=877861888, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=887778304, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=887795520, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=897711936, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=897716544, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=897721152, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=897725760, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=900379968, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=900384576, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=903038784, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=903043392, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=905697600, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=905702208, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=908356416, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=908361024, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=908365632, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=908370240, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=918286656, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=918303872, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=928220288, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=928224896, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=928229504, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=928234112, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=930888320, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=930892928, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=933547136, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=933551744, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=936205952, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=936210560, shape:[1152, 1152, 1, 1], type = f16
clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=938864768, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=938869376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=938873984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=938878592, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=948795008, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=948812224, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=958728640, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=958733248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=958737856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=958742464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=958747072, shape:[1152, 1, 1, 1], type = f32
load_hparams: projector: resampler
load_hparams: n_embd: 1152
load_hparams: n_head: 16
load_hparams: n_ff: 4304
load_hparams: n_layer: 27
load_hparams: projection_dim: 0
load_hparams: image_size: 448
load_hparams: patch_size: 14

load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 5
load_hparams: proj_scale_factor: 0
load_hparams: n_wa_pattern: 0
load_hparams: ffn_op: gelu
load_hparams: model size: 914.34 MiB
load_hparams: metadata size: 0.16 MiB
load_tensors: loaded 455 tensors from E:\AI\Ollama\blobs\sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761
clip.cpp:3782: Unknown minicpmv version
time=2025-08-11T21:16:07.316+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-08-11T21:16:07.566+03:00 level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409"
[GIN] 2025/08/11 - 21:16:07 | 500 | 5.4620974s | 127.0.0.1 | POST "/api/chat"
time=2025-08-11T21:16:12.601+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0309275 runner.size="3.8 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=26968 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-11T21:16:12.848+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2811761 runner.size="3.8 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=26968 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-11T21:16:13.098+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5313937 runner.size="3.8 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=26968 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b

<!-- gh-comment-id:3176313035 --> @Alias4D commented on GitHub (Aug 11, 2025): time=2025-08-11T21:15:41.124+03:00 level=INFO source=routes.go:1304 msg="server config" env="map[CUDA_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_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\\AI\\Ollama 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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-08-11T21:15:41.132+03:00 level=INFO source=images.go:477 msg="total blobs: 132" time=2025-08-11T21:15:41.134+03:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" time=2025-08-11T21:15:41.137+03:00 level=INFO source=routes.go:1357 msg="Listening on [::]:11434 (version 0.11.4)" time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-08-11T21:15:41.137+03:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=10 efficiency=4 threads=16 time=2025-08-11T21:15:41.844+03:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-9587ec6b-451e-6399-d84f-22272b7cc6fd library=cuda compute=8.6 driver=12.8 name="NVIDIA GeForce RTX 3050 Laptop GPU" overhead="660.6 MiB" time=2025-08-11T21:15:41.846+03:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-9587ec6b-451e-6399-d84f-22272b7cc6fd library=cuda variant=v12 compute=8.6 driver=12.8 name="NVIDIA GeForce RTX 3050 Laptop GPU" total="4.0 GiB" available="3.2 GiB" time=2025-08-11T21:15:41.846+03:00 level=INFO source=routes.go:1398 msg="entering low vram mode" "total vram"="4.0 GiB" threshold="20.0 GiB" [GIN] 2025/08/11 - 21:15:44 | 404 | 5.7397ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/11 - 21:15:44 | 200 | 6.2476ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/11 - 21:15:45 | 404 | 3.3559ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/11 - 21:15:47 | 404 | 5.8923ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/11 - 21:15:51 | 404 | 2.4693ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/11 - 21:15:57 | 200 | 30.0835ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/11 - 21:16:02 | 200 | 6.8315ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/11 - 21:16:02 | 200 | 21.8138ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/08/11 - 21:16:02 | 200 | 19.5197ms | 127.0.0.1 | POST "/api/show" time=2025-08-11T21:16:02.157+03:00 level=INFO source=server.go:135 msg="system memory" total="15.7 GiB" free="7.9 GiB" free_swap="12.2 GiB" time=2025-08-11T21:16:02.158+03:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=33 layers.offload=25 layers.split="" memory.available="[3.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.8 GiB" memory.required.partial="3.2 GiB" memory.required.kv="128.0 MiB" memory.required.allocations="[3.2 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="147.1 MiB" memory.graph.full="284.0 MiB" memory.graph.partial="300.5 MiB" projector.weights="914.3 MiB" projector.graph="0 B" llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Model llama_model_loader: - kv 3: general.size_label str = 3.6B llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.context_length u32 = 32768 llama_model_loader: - kv 6: llama.embedding_length u32 = 2560 llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240 llama_model_loader: - kv 8: llama.attention.head_count u32 = 32 llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 12: llama.attention.key_length u32 = 128 llama_model_loader: - kv 13: llama.attention.value_length u32 = 128 llama_model_loader: - kv 14: llama.vocab_size u32 = 73448 llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 16: tokenizer.ggml.model str = llama llama_model_loader: - kv 17: tokenizer.ggml.pre str = default llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["<unk>", "<s>", "</s>", "<SEP>", "<C... llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440 llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 30: general.quantization_version u32 = 2 llama_model_loader: - kv 31: general.file_type u32 = 15 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 2.04 GiB (4.85 BPW) load: special tokens cache size = 92 load: token to piece cache size = 0.4342 MB print_info: arch = llama print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 3.61 B print_info: general.name = Model print_info: vocab type = SPM print_info: n_vocab = 73448 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 73440 '<|im_end|>' print_info: EOT token = 73440 '<|im_end|>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 2 '</s>' print_info: LF token = 1099 '<0x0A>' print_info: FIM PRE token = 73445 '<|fim_prefix|>' print_info: FIM SUF token = 73447 '<|fim_suffix|>' print_info: FIM MID token = 73446 '<|fim_middle|>' print_info: EOG token = 73440 '<|im_end|>' print_info: max token length = 48 llama_model_load: vocab only - skipping tensors time=2025-08-11T21:16:02.232+03:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\Users\\AL-NABAA\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model E:\\AI\\Ollama\\blobs\\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b --ctx-size 4096 --batch-size 512 --n-gpu-layers 25 --threads 6 --no-mmap --parallel 1 --mmproj E:\\AI\\Ollama\\blobs\\sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761 --port 64933" time=2025-08-11T21:16:02.237+03:00 level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-08-11T21:16:02.237+03:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-11T21:16:02.240+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" time=2025-08-11T21:16:02.264+03:00 level=INFO source=runner.go:815 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3050 Laptop GPU, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from C:\Users\AL-NABAA\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\AL-NABAA\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-08-11T21:16:03.070+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-08-11T21:16:03.072+03:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:64933" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3050 Laptop GPU) - 3303 MiB free llama_model_loader: loaded meta data with 32 key-value pairs and 291 tensors from E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Model llama_model_loader: - kv 3: general.size_label str = 3.6B llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.context_length u32 = 32768 llama_model_loader: - kv 6: llama.embedding_length u32 = 2560 llama_model_loader: - kv 7: llama.feed_forward_length u32 = 10240 llama_model_loader: - kv 8: llama.attention.head_count u32 = 32 llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 2 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 12: llama.attention.key_length u32 = 128 llama_model_loader: - kv 13: llama.attention.value_length u32 = 128 llama_model_loader: - kv 14: llama.vocab_size u32 = 73448 llama_model_loader: - kv 15: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 16: tokenizer.ggml.model str = llama llama_model_loader: - kv 17: tokenizer.ggml.pre str = default llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,73448] = ["<unk>", "<s>", "</s>", "<SEP>", "<C... llama_model_loader: - kv 19: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 73440 llama_model_loader: - kv 23: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 26: tokenizer.ggml.add_sep_token bool = false llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... llama_model_loader: - kv 29: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 30: general.quantization_version u32 = 2 llama_model_loader: - kv 31: general.file_type u32 = 15 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 2.04 GiB (4.85 BPW) load: special tokens cache size = 92 load: token to piece cache size = 0.4342 MB print_info: arch = llama print_info: vocab_only = 0 print_info: n_ctx_train = 32768 print_info: n_embd = 2560 print_info: n_layer = 32 print_info: n_head = 32 print_info: n_head_kv = 2 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_swa_pattern = 1 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 16 print_info: n_embd_k_gqa = 256 print_info: n_embd_v_gqa = 256 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-06 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: f_attn_scale = 0.0e+00 print_info: n_ff = 10240 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 0 print_info: rope scaling = linear print_info: freq_base_train = 10000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 32768 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 8B print_info: model params = 3.61 B print_info: general.name = Model print_info: vocab type = SPM print_info: n_vocab = 73448 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 73440 '<|im_end|>' print_info: EOT token = 73440 '<|im_end|>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 2 '</s>' print_info: LF token = 1099 '<0x0A>' print_info: FIM PRE token = 73445 '<|fim_prefix|>' print_info: FIM SUF token = 73447 '<|fim_suffix|>' print_info: FIM MID token = 73446 '<|fim_middle|>' print_info: EOG token = 73440 '<|im_end|>' print_info: max token length = 48 load_tensors: loading model tensors, this can take a while... (mmap = false) time=2025-08-11T21:16:03.244+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" load_tensors: offloading 25 repeating layers to GPU load_tensors: offloaded 25/33 layers to GPU load_tensors: CUDA_Host model buffer size = 559.26 MiB load_tensors: CUDA0 model buffer size = 1426.67 MiB load_tensors: CPU model buffer size = 100.87 MiB llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 4096 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 512 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = 0 llama_context: freq_base = 10000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized llama_context: CPU output buffer size = 0.29 MiB llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1, padding = 32 llama_kv_cache_unified: CUDA0 KV buffer size = 100.00 MiB llama_kv_cache_unified: CPU KV buffer size = 28.00 MiB llama_kv_cache_unified: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB llama_context: CUDA0 compute buffer size = 298.25 MiB llama_context: CUDA_Host compute buffer size = 13.01 MiB llama_context: graph nodes = 1094 llama_context: graph splits = 81 (with bs=512), 3 (with bs=1) clip_ctx: CLIP using CUDA0 backend clip_model_loader: model name: clip_model_loader: description: image encoder for MiniCPM-V clip_model_loader: GGUF version: 3 clip_model_loader: alignment: 32 clip_model_loader: n_tensors: 455 clip_model_loader: n_kv: 19 clip_model_loader: tensor[0]: n_dims = 2, name = resampler.query, tensor_size=655360, offset=0, shape:[2560, 64, 1, 1], type = f32 clip_model_loader: tensor[1]: n_dims = 2, name = resampler.pos_embed_k, tensor_size=50176000, offset=655360, shape:[2560, 4900, 1, 1], type = f32 clip_model_loader: tensor[2]: n_dims = 2, name = resampler.proj.weight, tensor_size=13107200, offset=50831360, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[3]: n_dims = 2, name = resampler.kv.weight, tensor_size=5898240, offset=63938560, shape:[1152, 2560, 1, 1], type = f16 clip_model_loader: tensor[4]: n_dims = 2, name = resampler.attn.q.weight, tensor_size=13107200, offset=69836800, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[5]: n_dims = 2, name = resampler.attn.k.weight, tensor_size=13107200, offset=82944000, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[6]: n_dims = 2, name = resampler.attn.v.weight, tensor_size=13107200, offset=96051200, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[7]: n_dims = 1, name = resampler.attn.q.bias, tensor_size=10240, offset=109158400, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[8]: n_dims = 1, name = resampler.attn.k.bias, tensor_size=10240, offset=109168640, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[9]: n_dims = 1, name = resampler.attn.v.bias, tensor_size=10240, offset=109178880, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[10]: n_dims = 2, name = resampler.attn.out.weight, tensor_size=13107200, offset=109189120, shape:[2560, 2560, 1, 1], type = f16 clip_model_loader: tensor[11]: n_dims = 1, name = resampler.attn.out.bias, tensor_size=10240, offset=122296320, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[12]: n_dims = 1, name = resampler.ln_q.weight, tensor_size=10240, offset=122306560, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[13]: n_dims = 1, name = resampler.ln_q.bias, tensor_size=10240, offset=122316800, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[14]: n_dims = 1, name = resampler.ln_kv.weight, tensor_size=10240, offset=122327040, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[15]: n_dims = 1, name = resampler.ln_kv.bias, tensor_size=10240, offset=122337280, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[16]: n_dims = 1, name = resampler.ln_post.weight, tensor_size=10240, offset=122347520, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[17]: n_dims = 1, name = resampler.ln_post.bias, tensor_size=10240, offset=122357760, shape:[2560, 1, 1, 1], type = f32 clip_model_loader: tensor[18]: n_dims = 4, name = v.patch_embd.weight, tensor_size=1354752, offset=122368000, shape:[14, 14, 3, 1152], type = f16 clip_model_loader: tensor[19]: n_dims = 1, name = v.patch_embd.bias, tensor_size=4608, offset=123722752, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[20]: n_dims = 2, name = v.position_embd.weight, tensor_size=11289600, offset=123727360, shape:[1152, 4900, 1, 1], type = f16 clip_model_loader: tensor[21]: n_dims = 2, name = v.blk.0.attn_k.weight, tensor_size=2654208, offset=135016960, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[22]: n_dims = 1, name = v.blk.0.attn_k.bias, tensor_size=4608, offset=137671168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[23]: n_dims = 2, name = v.blk.0.attn_v.weight, tensor_size=2654208, offset=137675776, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[24]: n_dims = 1, name = v.blk.0.attn_v.bias, tensor_size=4608, offset=140329984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[25]: n_dims = 2, name = v.blk.0.attn_q.weight, tensor_size=2654208, offset=140334592, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[26]: n_dims = 1, name = v.blk.0.attn_q.bias, tensor_size=4608, offset=142988800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[27]: n_dims = 2, name = v.blk.0.attn_out.weight, tensor_size=2654208, offset=142993408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[28]: n_dims = 1, name = v.blk.0.attn_out.bias, tensor_size=4608, offset=145647616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[29]: n_dims = 1, name = v.blk.0.ln1.weight, tensor_size=4608, offset=145652224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[30]: n_dims = 1, name = v.blk.0.ln1.bias, tensor_size=4608, offset=145656832, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[31]: n_dims = 2, name = v.blk.0.ffn_down.weight, tensor_size=9916416, offset=145661440, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[32]: n_dims = 1, name = v.blk.0.ffn_down.bias, tensor_size=17216, offset=155577856, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[33]: n_dims = 2, name = v.blk.0.ffn_up.weight, tensor_size=9916416, offset=155595072, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[34]: n_dims = 1, name = v.blk.0.ffn_up.bias, tensor_size=4608, offset=165511488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[35]: n_dims = 1, name = v.blk.0.ln2.weight, tensor_size=4608, offset=165516096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[36]: n_dims = 1, name = v.blk.0.ln2.bias, tensor_size=4608, offset=165520704, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[37]: n_dims = 2, name = v.blk.1.attn_k.weight, tensor_size=2654208, offset=165525312, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[38]: n_dims = 1, name = v.blk.1.attn_k.bias, tensor_size=4608, offset=168179520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[39]: n_dims = 2, name = v.blk.1.attn_v.weight, tensor_size=2654208, offset=168184128, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[40]: n_dims = 1, name = v.blk.1.attn_v.bias, tensor_size=4608, offset=170838336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[41]: n_dims = 2, name = v.blk.1.attn_q.weight, tensor_size=2654208, offset=170842944, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[42]: n_dims = 1, name = v.blk.1.attn_q.bias, tensor_size=4608, offset=173497152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[43]: n_dims = 2, name = v.blk.1.attn_out.weight, tensor_size=2654208, offset=173501760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[44]: n_dims = 1, name = v.blk.1.attn_out.bias, tensor_size=4608, offset=176155968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[45]: n_dims = 1, name = v.blk.1.ln1.weight, tensor_size=4608, offset=176160576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[46]: n_dims = 1, name = v.blk.1.ln1.bias, tensor_size=4608, offset=176165184, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[47]: n_dims = 2, name = v.blk.1.ffn_down.weight, tensor_size=9916416, offset=176169792, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[48]: n_dims = 1, name = v.blk.1.ffn_down.bias, tensor_size=17216, offset=186086208, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[49]: n_dims = 2, name = v.blk.1.ffn_up.weight, tensor_size=9916416, offset=186103424, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[50]: n_dims = 1, name = v.blk.1.ffn_up.bias, tensor_size=4608, offset=196019840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[51]: n_dims = 1, name = v.blk.1.ln2.weight, tensor_size=4608, offset=196024448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[52]: n_dims = 1, name = v.blk.1.ln2.bias, tensor_size=4608, offset=196029056, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[53]: n_dims = 2, name = v.blk.2.attn_k.weight, tensor_size=2654208, offset=196033664, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[54]: n_dims = 1, name = v.blk.2.attn_k.bias, tensor_size=4608, offset=198687872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[55]: n_dims = 2, name = v.blk.2.attn_v.weight, tensor_size=2654208, offset=198692480, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[56]: n_dims = 1, name = v.blk.2.attn_v.bias, tensor_size=4608, offset=201346688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[57]: n_dims = 2, name = v.blk.2.attn_q.weight, tensor_size=2654208, offset=201351296, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[58]: n_dims = 1, name = v.blk.2.attn_q.bias, tensor_size=4608, offset=204005504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[59]: n_dims = 2, name = v.blk.2.attn_out.weight, tensor_size=2654208, offset=204010112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[60]: n_dims = 1, name = v.blk.2.attn_out.bias, tensor_size=4608, offset=206664320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[61]: n_dims = 1, name = v.blk.2.ln1.weight, tensor_size=4608, offset=206668928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[62]: n_dims = 1, name = v.blk.2.ln1.bias, tensor_size=4608, offset=206673536, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[63]: n_dims = 2, name = v.blk.2.ffn_down.weight, tensor_size=9916416, offset=206678144, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[64]: n_dims = 1, name = v.blk.2.ffn_down.bias, tensor_size=17216, offset=216594560, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[65]: n_dims = 2, name = v.blk.2.ffn_up.weight, tensor_size=9916416, offset=216611776, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[66]: n_dims = 1, name = v.blk.2.ffn_up.bias, tensor_size=4608, offset=226528192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[67]: n_dims = 1, name = v.blk.2.ln2.weight, tensor_size=4608, offset=226532800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[68]: n_dims = 1, name = v.blk.2.ln2.bias, tensor_size=4608, offset=226537408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[69]: n_dims = 2, name = v.blk.3.attn_k.weight, tensor_size=2654208, offset=226542016, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[70]: n_dims = 1, name = v.blk.3.attn_k.bias, tensor_size=4608, offset=229196224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[71]: n_dims = 2, name = v.blk.3.attn_v.weight, tensor_size=2654208, offset=229200832, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[72]: n_dims = 1, name = v.blk.3.attn_v.bias, tensor_size=4608, offset=231855040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[73]: n_dims = 2, name = v.blk.3.attn_q.weight, tensor_size=2654208, offset=231859648, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[74]: n_dims = 1, name = v.blk.3.attn_q.bias, tensor_size=4608, offset=234513856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[75]: n_dims = 2, name = v.blk.3.attn_out.weight, tensor_size=2654208, offset=234518464, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[76]: n_dims = 1, name = v.blk.3.attn_out.bias, tensor_size=4608, offset=237172672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[77]: n_dims = 1, name = v.blk.3.ln1.weight, tensor_size=4608, offset=237177280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[78]: n_dims = 1, name = v.blk.3.ln1.bias, tensor_size=4608, offset=237181888, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[79]: n_dims = 2, name = v.blk.3.ffn_down.weight, tensor_size=9916416, offset=237186496, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[80]: n_dims = 1, name = v.blk.3.ffn_down.bias, tensor_size=17216, offset=247102912, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[81]: n_dims = 2, name = v.blk.3.ffn_up.weight, tensor_size=9916416, offset=247120128, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[82]: n_dims = 1, name = v.blk.3.ffn_up.bias, tensor_size=4608, offset=257036544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[83]: n_dims = 1, name = v.blk.3.ln2.weight, tensor_size=4608, offset=257041152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[84]: n_dims = 1, name = v.blk.3.ln2.bias, tensor_size=4608, offset=257045760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[85]: n_dims = 2, name = v.blk.4.attn_k.weight, tensor_size=2654208, offset=257050368, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[86]: n_dims = 1, name = v.blk.4.attn_k.bias, tensor_size=4608, offset=259704576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[87]: n_dims = 2, name = v.blk.4.attn_v.weight, tensor_size=2654208, offset=259709184, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[88]: n_dims = 1, name = v.blk.4.attn_v.bias, tensor_size=4608, offset=262363392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[89]: n_dims = 2, name = v.blk.4.attn_q.weight, tensor_size=2654208, offset=262368000, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[90]: n_dims = 1, name = v.blk.4.attn_q.bias, tensor_size=4608, offset=265022208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[91]: n_dims = 2, name = v.blk.4.attn_out.weight, tensor_size=2654208, offset=265026816, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[92]: n_dims = 1, name = v.blk.4.attn_out.bias, tensor_size=4608, offset=267681024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[93]: n_dims = 1, name = v.blk.4.ln1.weight, tensor_size=4608, offset=267685632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[94]: n_dims = 1, name = v.blk.4.ln1.bias, tensor_size=4608, offset=267690240, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[95]: n_dims = 2, name = v.blk.4.ffn_down.weight, tensor_size=9916416, offset=267694848, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[96]: n_dims = 1, name = v.blk.4.ffn_down.bias, tensor_size=17216, offset=277611264, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[97]: n_dims = 2, name = v.blk.4.ffn_up.weight, tensor_size=9916416, offset=277628480, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[98]: n_dims = 1, name = v.blk.4.ffn_up.bias, tensor_size=4608, offset=287544896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[99]: n_dims = 1, name = v.blk.4.ln2.weight, tensor_size=4608, offset=287549504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[100]: n_dims = 1, name = v.blk.4.ln2.bias, tensor_size=4608, offset=287554112, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[101]: n_dims = 2, name = v.blk.5.attn_k.weight, tensor_size=2654208, offset=287558720, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[102]: n_dims = 1, name = v.blk.5.attn_k.bias, tensor_size=4608, offset=290212928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[103]: n_dims = 2, name = v.blk.5.attn_v.weight, tensor_size=2654208, offset=290217536, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[104]: n_dims = 1, name = v.blk.5.attn_v.bias, tensor_size=4608, offset=292871744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[105]: n_dims = 2, name = v.blk.5.attn_q.weight, tensor_size=2654208, offset=292876352, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[106]: n_dims = 1, name = v.blk.5.attn_q.bias, tensor_size=4608, offset=295530560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[107]: n_dims = 2, name = v.blk.5.attn_out.weight, tensor_size=2654208, offset=295535168, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[108]: n_dims = 1, name = v.blk.5.attn_out.bias, tensor_size=4608, offset=298189376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[109]: n_dims = 1, name = v.blk.5.ln1.weight, tensor_size=4608, offset=298193984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[110]: n_dims = 1, name = v.blk.5.ln1.bias, tensor_size=4608, offset=298198592, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[111]: n_dims = 2, name = v.blk.5.ffn_down.weight, tensor_size=9916416, offset=298203200, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[112]: n_dims = 1, name = v.blk.5.ffn_down.bias, tensor_size=17216, offset=308119616, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[113]: n_dims = 2, name = v.blk.5.ffn_up.weight, tensor_size=9916416, offset=308136832, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[114]: n_dims = 1, name = v.blk.5.ffn_up.bias, tensor_size=4608, offset=318053248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[115]: n_dims = 1, name = v.blk.5.ln2.weight, tensor_size=4608, offset=318057856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[116]: n_dims = 1, name = v.blk.5.ln2.bias, tensor_size=4608, offset=318062464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[117]: n_dims = 2, name = v.blk.6.attn_k.weight, tensor_size=2654208, offset=318067072, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[118]: n_dims = 1, name = v.blk.6.attn_k.bias, tensor_size=4608, offset=320721280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[119]: n_dims = 2, name = v.blk.6.attn_v.weight, tensor_size=2654208, offset=320725888, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[120]: n_dims = 1, name = v.blk.6.attn_v.bias, tensor_size=4608, offset=323380096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[121]: n_dims = 2, name = v.blk.6.attn_q.weight, tensor_size=2654208, offset=323384704, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[122]: n_dims = 1, name = v.blk.6.attn_q.bias, tensor_size=4608, offset=326038912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[123]: n_dims = 2, name = v.blk.6.attn_out.weight, tensor_size=2654208, offset=326043520, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[124]: n_dims = 1, name = v.blk.6.attn_out.bias, tensor_size=4608, offset=328697728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[125]: n_dims = 1, name = v.blk.6.ln1.weight, tensor_size=4608, offset=328702336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[126]: n_dims = 1, name = v.blk.6.ln1.bias, tensor_size=4608, offset=328706944, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[127]: n_dims = 2, name = v.blk.6.ffn_down.weight, tensor_size=9916416, offset=328711552, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[128]: n_dims = 1, name = v.blk.6.ffn_down.bias, tensor_size=17216, offset=338627968, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[129]: n_dims = 2, name = v.blk.6.ffn_up.weight, tensor_size=9916416, offset=338645184, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[130]: n_dims = 1, name = v.blk.6.ffn_up.bias, tensor_size=4608, offset=348561600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[131]: n_dims = 1, name = v.blk.6.ln2.weight, tensor_size=4608, offset=348566208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[132]: n_dims = 1, name = v.blk.6.ln2.bias, tensor_size=4608, offset=348570816, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[133]: n_dims = 2, name = v.blk.7.attn_k.weight, tensor_size=2654208, offset=348575424, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[134]: n_dims = 1, name = v.blk.7.attn_k.bias, tensor_size=4608, offset=351229632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[135]: n_dims = 2, name = v.blk.7.attn_v.weight, tensor_size=2654208, offset=351234240, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[136]: n_dims = 1, name = v.blk.7.attn_v.bias, tensor_size=4608, offset=353888448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[137]: n_dims = 2, name = v.blk.7.attn_q.weight, tensor_size=2654208, offset=353893056, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[138]: n_dims = 1, name = v.blk.7.attn_q.bias, tensor_size=4608, offset=356547264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[139]: n_dims = 2, name = v.blk.7.attn_out.weight, tensor_size=2654208, offset=356551872, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[140]: n_dims = 1, name = v.blk.7.attn_out.bias, tensor_size=4608, offset=359206080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[141]: n_dims = 1, name = v.blk.7.ln1.weight, tensor_size=4608, offset=359210688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[142]: n_dims = 1, name = v.blk.7.ln1.bias, tensor_size=4608, offset=359215296, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[143]: n_dims = 2, name = v.blk.7.ffn_down.weight, tensor_size=9916416, offset=359219904, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[144]: n_dims = 1, name = v.blk.7.ffn_down.bias, tensor_size=17216, offset=369136320, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[145]: n_dims = 2, name = v.blk.7.ffn_up.weight, tensor_size=9916416, offset=369153536, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[146]: n_dims = 1, name = v.blk.7.ffn_up.bias, tensor_size=4608, offset=379069952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[147]: n_dims = 1, name = v.blk.7.ln2.weight, tensor_size=4608, offset=379074560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[148]: n_dims = 1, name = v.blk.7.ln2.bias, tensor_size=4608, offset=379079168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[149]: n_dims = 2, name = v.blk.8.attn_k.weight, tensor_size=2654208, offset=379083776, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[150]: n_dims = 1, name = v.blk.8.attn_k.bias, tensor_size=4608, offset=381737984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[151]: n_dims = 2, name = v.blk.8.attn_v.weight, tensor_size=2654208, offset=381742592, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[152]: n_dims = 1, name = v.blk.8.attn_v.bias, tensor_size=4608, offset=384396800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[153]: n_dims = 2, name = v.blk.8.attn_q.weight, tensor_size=2654208, offset=384401408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[154]: n_dims = 1, name = v.blk.8.attn_q.bias, tensor_size=4608, offset=387055616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[155]: n_dims = 2, name = v.blk.8.attn_out.weight, tensor_size=2654208, offset=387060224, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[156]: n_dims = 1, name = v.blk.8.attn_out.bias, tensor_size=4608, offset=389714432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[157]: n_dims = 1, name = v.blk.8.ln1.weight, tensor_size=4608, offset=389719040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[158]: n_dims = 1, name = v.blk.8.ln1.bias, tensor_size=4608, offset=389723648, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[159]: n_dims = 2, name = v.blk.8.ffn_down.weight, tensor_size=9916416, offset=389728256, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[160]: n_dims = 1, name = v.blk.8.ffn_down.bias, tensor_size=17216, offset=399644672, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[161]: n_dims = 2, name = v.blk.8.ffn_up.weight, tensor_size=9916416, offset=399661888, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[162]: n_dims = 1, name = v.blk.8.ffn_up.bias, tensor_size=4608, offset=409578304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[163]: n_dims = 1, name = v.blk.8.ln2.weight, tensor_size=4608, offset=409582912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[164]: n_dims = 1, name = v.blk.8.ln2.bias, tensor_size=4608, offset=409587520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[165]: n_dims = 2, name = v.blk.9.attn_k.weight, tensor_size=2654208, offset=409592128, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[166]: n_dims = 1, name = v.blk.9.attn_k.bias, tensor_size=4608, offset=412246336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[167]: n_dims = 2, name = v.blk.9.attn_v.weight, tensor_size=2654208, offset=412250944, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[168]: n_dims = 1, name = v.blk.9.attn_v.bias, tensor_size=4608, offset=414905152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[169]: n_dims = 2, name = v.blk.9.attn_q.weight, tensor_size=2654208, offset=414909760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[170]: n_dims = 1, name = v.blk.9.attn_q.bias, tensor_size=4608, offset=417563968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[171]: n_dims = 2, name = v.blk.9.attn_out.weight, tensor_size=2654208, offset=417568576, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[172]: n_dims = 1, name = v.blk.9.attn_out.bias, tensor_size=4608, offset=420222784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[173]: n_dims = 1, name = v.blk.9.ln1.weight, tensor_size=4608, offset=420227392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[174]: n_dims = 1, name = v.blk.9.ln1.bias, tensor_size=4608, offset=420232000, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[175]: n_dims = 2, name = v.blk.9.ffn_down.weight, tensor_size=9916416, offset=420236608, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[176]: n_dims = 1, name = v.blk.9.ffn_down.bias, tensor_size=17216, offset=430153024, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[177]: n_dims = 2, name = v.blk.9.ffn_up.weight, tensor_size=9916416, offset=430170240, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[178]: n_dims = 1, name = v.blk.9.ffn_up.bias, tensor_size=4608, offset=440086656, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[179]: n_dims = 1, name = v.blk.9.ln2.weight, tensor_size=4608, offset=440091264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[180]: n_dims = 1, name = v.blk.9.ln2.bias, tensor_size=4608, offset=440095872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[181]: n_dims = 2, name = v.blk.10.attn_k.weight, tensor_size=2654208, offset=440100480, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[182]: n_dims = 1, name = v.blk.10.attn_k.bias, tensor_size=4608, offset=442754688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[183]: n_dims = 2, name = v.blk.10.attn_v.weight, tensor_size=2654208, offset=442759296, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[184]: n_dims = 1, name = v.blk.10.attn_v.bias, tensor_size=4608, offset=445413504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[185]: n_dims = 2, name = v.blk.10.attn_q.weight, tensor_size=2654208, offset=445418112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[186]: n_dims = 1, name = v.blk.10.attn_q.bias, tensor_size=4608, offset=448072320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[187]: n_dims = 2, name = v.blk.10.attn_out.weight, tensor_size=2654208, offset=448076928, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[188]: n_dims = 1, name = v.blk.10.attn_out.bias, tensor_size=4608, offset=450731136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[189]: n_dims = 1, name = v.blk.10.ln1.weight, tensor_size=4608, offset=450735744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[190]: n_dims = 1, name = v.blk.10.ln1.bias, tensor_size=4608, offset=450740352, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[191]: n_dims = 2, name = v.blk.10.ffn_down.weight, tensor_size=9916416, offset=450744960, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[192]: n_dims = 1, name = v.blk.10.ffn_down.bias, tensor_size=17216, offset=460661376, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[193]: n_dims = 2, name = v.blk.10.ffn_up.weight, tensor_size=9916416, offset=460678592, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[194]: n_dims = 1, name = v.blk.10.ffn_up.bias, tensor_size=4608, offset=470595008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[195]: n_dims = 1, name = v.blk.10.ln2.weight, tensor_size=4608, offset=470599616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[196]: n_dims = 1, name = v.blk.10.ln2.bias, tensor_size=4608, offset=470604224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[197]: n_dims = 2, name = v.blk.11.attn_k.weight, tensor_size=2654208, offset=470608832, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[198]: n_dims = 1, name = v.blk.11.attn_k.bias, tensor_size=4608, offset=473263040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[199]: n_dims = 2, name = v.blk.11.attn_v.weight, tensor_size=2654208, offset=473267648, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[200]: n_dims = 1, name = v.blk.11.attn_v.bias, tensor_size=4608, offset=475921856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[201]: n_dims = 2, name = v.blk.11.attn_q.weight, tensor_size=2654208, offset=475926464, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[202]: n_dims = 1, name = v.blk.11.attn_q.bias, tensor_size=4608, offset=478580672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[203]: n_dims = 2, name = v.blk.11.attn_out.weight, tensor_size=2654208, offset=478585280, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[204]: n_dims = 1, name = v.blk.11.attn_out.bias, tensor_size=4608, offset=481239488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[205]: n_dims = 1, name = v.blk.11.ln1.weight, tensor_size=4608, offset=481244096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[206]: n_dims = 1, name = v.blk.11.ln1.bias, tensor_size=4608, offset=481248704, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[207]: n_dims = 2, name = v.blk.11.ffn_down.weight, tensor_size=9916416, offset=481253312, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[208]: n_dims = 1, name = v.blk.11.ffn_down.bias, tensor_size=17216, offset=491169728, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[209]: n_dims = 2, name = v.blk.11.ffn_up.weight, tensor_size=9916416, offset=491186944, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[210]: n_dims = 1, name = v.blk.11.ffn_up.bias, tensor_size=4608, offset=501103360, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[211]: n_dims = 1, name = v.blk.11.ln2.weight, tensor_size=4608, offset=501107968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[212]: n_dims = 1, name = v.blk.11.ln2.bias, tensor_size=4608, offset=501112576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[213]: n_dims = 2, name = v.blk.12.attn_k.weight, tensor_size=2654208, offset=501117184, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[214]: n_dims = 1, name = v.blk.12.attn_k.bias, tensor_size=4608, offset=503771392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[215]: n_dims = 2, name = v.blk.12.attn_v.weight, tensor_size=2654208, offset=503776000, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[216]: n_dims = 1, name = v.blk.12.attn_v.bias, tensor_size=4608, offset=506430208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[217]: n_dims = 2, name = v.blk.12.attn_q.weight, tensor_size=2654208, offset=506434816, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[218]: n_dims = 1, name = v.blk.12.attn_q.bias, tensor_size=4608, offset=509089024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[219]: n_dims = 2, name = v.blk.12.attn_out.weight, tensor_size=2654208, offset=509093632, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[220]: n_dims = 1, name = v.blk.12.attn_out.bias, tensor_size=4608, offset=511747840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[221]: n_dims = 1, name = v.blk.12.ln1.weight, tensor_size=4608, offset=511752448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[222]: n_dims = 1, name = v.blk.12.ln1.bias, tensor_size=4608, offset=511757056, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[223]: n_dims = 2, name = v.blk.12.ffn_down.weight, tensor_size=9916416, offset=511761664, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[224]: n_dims = 1, name = v.blk.12.ffn_down.bias, tensor_size=17216, offset=521678080, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[225]: n_dims = 2, name = v.blk.12.ffn_up.weight, tensor_size=9916416, offset=521695296, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[226]: n_dims = 1, name = v.blk.12.ffn_up.bias, tensor_size=4608, offset=531611712, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[227]: n_dims = 1, name = v.blk.12.ln2.weight, tensor_size=4608, offset=531616320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[228]: n_dims = 1, name = v.blk.12.ln2.bias, tensor_size=4608, offset=531620928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[229]: n_dims = 2, name = v.blk.13.attn_k.weight, tensor_size=2654208, offset=531625536, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[230]: n_dims = 1, name = v.blk.13.attn_k.bias, tensor_size=4608, offset=534279744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[231]: n_dims = 2, name = v.blk.13.attn_v.weight, tensor_size=2654208, offset=534284352, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[232]: n_dims = 1, name = v.blk.13.attn_v.bias, tensor_size=4608, offset=536938560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[233]: n_dims = 2, name = v.blk.13.attn_q.weight, tensor_size=2654208, offset=536943168, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[234]: n_dims = 1, name = v.blk.13.attn_q.bias, tensor_size=4608, offset=539597376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[235]: n_dims = 2, name = v.blk.13.attn_out.weight, tensor_size=2654208, offset=539601984, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[236]: n_dims = 1, name = v.blk.13.attn_out.bias, tensor_size=4608, offset=542256192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[237]: n_dims = 1, name = v.blk.13.ln1.weight, tensor_size=4608, offset=542260800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[238]: n_dims = 1, name = v.blk.13.ln1.bias, tensor_size=4608, offset=542265408, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[239]: n_dims = 2, name = v.blk.13.ffn_down.weight, tensor_size=9916416, offset=542270016, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[240]: n_dims = 1, name = v.blk.13.ffn_down.bias, tensor_size=17216, offset=552186432, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[241]: n_dims = 2, name = v.blk.13.ffn_up.weight, tensor_size=9916416, offset=552203648, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[242]: n_dims = 1, name = v.blk.13.ffn_up.bias, tensor_size=4608, offset=562120064, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[243]: n_dims = 1, name = v.blk.13.ln2.weight, tensor_size=4608, offset=562124672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[244]: n_dims = 1, name = v.blk.13.ln2.bias, tensor_size=4608, offset=562129280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[245]: n_dims = 2, name = v.blk.14.attn_k.weight, tensor_size=2654208, offset=562133888, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[246]: n_dims = 1, name = v.blk.14.attn_k.bias, tensor_size=4608, offset=564788096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[247]: n_dims = 2, name = v.blk.14.attn_v.weight, tensor_size=2654208, offset=564792704, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[248]: n_dims = 1, name = v.blk.14.attn_v.bias, tensor_size=4608, offset=567446912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[249]: n_dims = 2, name = v.blk.14.attn_q.weight, tensor_size=2654208, offset=567451520, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[250]: n_dims = 1, name = v.blk.14.attn_q.bias, tensor_size=4608, offset=570105728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[251]: n_dims = 2, name = v.blk.14.attn_out.weight, tensor_size=2654208, offset=570110336, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[252]: n_dims = 1, name = v.blk.14.attn_out.bias, tensor_size=4608, offset=572764544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[253]: n_dims = 1, name = v.blk.14.ln1.weight, tensor_size=4608, offset=572769152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[254]: n_dims = 1, name = v.blk.14.ln1.bias, tensor_size=4608, offset=572773760, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[255]: n_dims = 2, name = v.blk.14.ffn_down.weight, tensor_size=9916416, offset=572778368, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[256]: n_dims = 1, name = v.blk.14.ffn_down.bias, tensor_size=17216, offset=582694784, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[257]: n_dims = 2, name = v.blk.14.ffn_up.weight, tensor_size=9916416, offset=582712000, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[258]: n_dims = 1, name = v.blk.14.ffn_up.bias, tensor_size=4608, offset=592628416, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[259]: n_dims = 1, name = v.blk.14.ln2.weight, tensor_size=4608, offset=592633024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[260]: n_dims = 1, name = v.blk.14.ln2.bias, tensor_size=4608, offset=592637632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[261]: n_dims = 2, name = v.blk.15.attn_k.weight, tensor_size=2654208, offset=592642240, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[262]: n_dims = 1, name = v.blk.15.attn_k.bias, tensor_size=4608, offset=595296448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[263]: n_dims = 2, name = v.blk.15.attn_v.weight, tensor_size=2654208, offset=595301056, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[264]: n_dims = 1, name = v.blk.15.attn_v.bias, tensor_size=4608, offset=597955264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[265]: n_dims = 2, name = v.blk.15.attn_q.weight, tensor_size=2654208, offset=597959872, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[266]: n_dims = 1, name = v.blk.15.attn_q.bias, tensor_size=4608, offset=600614080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[267]: n_dims = 2, name = v.blk.15.attn_out.weight, tensor_size=2654208, offset=600618688, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[268]: n_dims = 1, name = v.blk.15.attn_out.bias, tensor_size=4608, offset=603272896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[269]: n_dims = 1, name = v.blk.15.ln1.weight, tensor_size=4608, offset=603277504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[270]: n_dims = 1, name = v.blk.15.ln1.bias, tensor_size=4608, offset=603282112, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[271]: n_dims = 2, name = v.blk.15.ffn_down.weight, tensor_size=9916416, offset=603286720, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[272]: n_dims = 1, name = v.blk.15.ffn_down.bias, tensor_size=17216, offset=613203136, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[273]: n_dims = 2, name = v.blk.15.ffn_up.weight, tensor_size=9916416, offset=613220352, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[274]: n_dims = 1, name = v.blk.15.ffn_up.bias, tensor_size=4608, offset=623136768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[275]: n_dims = 1, name = v.blk.15.ln2.weight, tensor_size=4608, offset=623141376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[276]: n_dims = 1, name = v.blk.15.ln2.bias, tensor_size=4608, offset=623145984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[277]: n_dims = 2, name = v.blk.16.attn_k.weight, tensor_size=2654208, offset=623150592, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[278]: n_dims = 1, name = v.blk.16.attn_k.bias, tensor_size=4608, offset=625804800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[279]: n_dims = 2, name = v.blk.16.attn_v.weight, tensor_size=2654208, offset=625809408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[280]: n_dims = 1, name = v.blk.16.attn_v.bias, tensor_size=4608, offset=628463616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[281]: n_dims = 2, name = v.blk.16.attn_q.weight, tensor_size=2654208, offset=628468224, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[282]: n_dims = 1, name = v.blk.16.attn_q.bias, tensor_size=4608, offset=631122432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[283]: n_dims = 2, name = v.blk.16.attn_out.weight, tensor_size=2654208, offset=631127040, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[284]: n_dims = 1, name = v.blk.16.attn_out.bias, tensor_size=4608, offset=633781248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[285]: n_dims = 1, name = v.blk.16.ln1.weight, tensor_size=4608, offset=633785856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[286]: n_dims = 1, name = v.blk.16.ln1.bias, tensor_size=4608, offset=633790464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[287]: n_dims = 2, name = v.blk.16.ffn_down.weight, tensor_size=9916416, offset=633795072, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[288]: n_dims = 1, name = v.blk.16.ffn_down.bias, tensor_size=17216, offset=643711488, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[289]: n_dims = 2, name = v.blk.16.ffn_up.weight, tensor_size=9916416, offset=643728704, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[290]: n_dims = 1, name = v.blk.16.ffn_up.bias, tensor_size=4608, offset=653645120, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[291]: n_dims = 1, name = v.blk.16.ln2.weight, tensor_size=4608, offset=653649728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[292]: n_dims = 1, name = v.blk.16.ln2.bias, tensor_size=4608, offset=653654336, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[293]: n_dims = 2, name = v.blk.17.attn_k.weight, tensor_size=2654208, offset=653658944, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[294]: n_dims = 1, name = v.blk.17.attn_k.bias, tensor_size=4608, offset=656313152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[295]: n_dims = 2, name = v.blk.17.attn_v.weight, tensor_size=2654208, offset=656317760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[296]: n_dims = 1, name = v.blk.17.attn_v.bias, tensor_size=4608, offset=658971968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[297]: n_dims = 2, name = v.blk.17.attn_q.weight, tensor_size=2654208, offset=658976576, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[298]: n_dims = 1, name = v.blk.17.attn_q.bias, tensor_size=4608, offset=661630784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[299]: n_dims = 2, name = v.blk.17.attn_out.weight, tensor_size=2654208, offset=661635392, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[300]: n_dims = 1, name = v.blk.17.attn_out.bias, tensor_size=4608, offset=664289600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[301]: n_dims = 1, name = v.blk.17.ln1.weight, tensor_size=4608, offset=664294208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[302]: n_dims = 1, name = v.blk.17.ln1.bias, tensor_size=4608, offset=664298816, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[303]: n_dims = 2, name = v.blk.17.ffn_down.weight, tensor_size=9916416, offset=664303424, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[304]: n_dims = 1, name = v.blk.17.ffn_down.bias, tensor_size=17216, offset=674219840, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[305]: n_dims = 2, name = v.blk.17.ffn_up.weight, tensor_size=9916416, offset=674237056, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[306]: n_dims = 1, name = v.blk.17.ffn_up.bias, tensor_size=4608, offset=684153472, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[307]: n_dims = 1, name = v.blk.17.ln2.weight, tensor_size=4608, offset=684158080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[308]: n_dims = 1, name = v.blk.17.ln2.bias, tensor_size=4608, offset=684162688, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[309]: n_dims = 2, name = v.blk.18.attn_k.weight, tensor_size=2654208, offset=684167296, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[310]: n_dims = 1, name = v.blk.18.attn_k.bias, tensor_size=4608, offset=686821504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[311]: n_dims = 2, name = v.blk.18.attn_v.weight, tensor_size=2654208, offset=686826112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[312]: n_dims = 1, name = v.blk.18.attn_v.bias, tensor_size=4608, offset=689480320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[313]: n_dims = 2, name = v.blk.18.attn_q.weight, tensor_size=2654208, offset=689484928, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[314]: n_dims = 1, name = v.blk.18.attn_q.bias, tensor_size=4608, offset=692139136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[315]: n_dims = 2, name = v.blk.18.attn_out.weight, tensor_size=2654208, offset=692143744, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[316]: n_dims = 1, name = v.blk.18.attn_out.bias, tensor_size=4608, offset=694797952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[317]: n_dims = 1, name = v.blk.18.ln1.weight, tensor_size=4608, offset=694802560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[318]: n_dims = 1, name = v.blk.18.ln1.bias, tensor_size=4608, offset=694807168, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[319]: n_dims = 2, name = v.blk.18.ffn_down.weight, tensor_size=9916416, offset=694811776, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[320]: n_dims = 1, name = v.blk.18.ffn_down.bias, tensor_size=17216, offset=704728192, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[321]: n_dims = 2, name = v.blk.18.ffn_up.weight, tensor_size=9916416, offset=704745408, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[322]: n_dims = 1, name = v.blk.18.ffn_up.bias, tensor_size=4608, offset=714661824, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[323]: n_dims = 1, name = v.blk.18.ln2.weight, tensor_size=4608, offset=714666432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[324]: n_dims = 1, name = v.blk.18.ln2.bias, tensor_size=4608, offset=714671040, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[325]: n_dims = 2, name = v.blk.19.attn_k.weight, tensor_size=2654208, offset=714675648, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[326]: n_dims = 1, name = v.blk.19.attn_k.bias, tensor_size=4608, offset=717329856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[327]: n_dims = 2, name = v.blk.19.attn_v.weight, tensor_size=2654208, offset=717334464, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[328]: n_dims = 1, name = v.blk.19.attn_v.bias, tensor_size=4608, offset=719988672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[329]: n_dims = 2, name = v.blk.19.attn_q.weight, tensor_size=2654208, offset=719993280, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[330]: n_dims = 1, name = v.blk.19.attn_q.bias, tensor_size=4608, offset=722647488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[331]: n_dims = 2, name = v.blk.19.attn_out.weight, tensor_size=2654208, offset=722652096, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[332]: n_dims = 1, name = v.blk.19.attn_out.bias, tensor_size=4608, offset=725306304, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[333]: n_dims = 1, name = v.blk.19.ln1.weight, tensor_size=4608, offset=725310912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[334]: n_dims = 1, name = v.blk.19.ln1.bias, tensor_size=4608, offset=725315520, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[335]: n_dims = 2, name = v.blk.19.ffn_down.weight, tensor_size=9916416, offset=725320128, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[336]: n_dims = 1, name = v.blk.19.ffn_down.bias, tensor_size=17216, offset=735236544, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[337]: n_dims = 2, name = v.blk.19.ffn_up.weight, tensor_size=9916416, offset=735253760, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[338]: n_dims = 1, name = v.blk.19.ffn_up.bias, tensor_size=4608, offset=745170176, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[339]: n_dims = 1, name = v.blk.19.ln2.weight, tensor_size=4608, offset=745174784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[340]: n_dims = 1, name = v.blk.19.ln2.bias, tensor_size=4608, offset=745179392, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[341]: n_dims = 2, name = v.blk.20.attn_k.weight, tensor_size=2654208, offset=745184000, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[342]: n_dims = 1, name = v.blk.20.attn_k.bias, tensor_size=4608, offset=747838208, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[343]: n_dims = 2, name = v.blk.20.attn_v.weight, tensor_size=2654208, offset=747842816, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[344]: n_dims = 1, name = v.blk.20.attn_v.bias, tensor_size=4608, offset=750497024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[345]: n_dims = 2, name = v.blk.20.attn_q.weight, tensor_size=2654208, offset=750501632, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[346]: n_dims = 1, name = v.blk.20.attn_q.bias, tensor_size=4608, offset=753155840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[347]: n_dims = 2, name = v.blk.20.attn_out.weight, tensor_size=2654208, offset=753160448, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[348]: n_dims = 1, name = v.blk.20.attn_out.bias, tensor_size=4608, offset=755814656, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[349]: n_dims = 1, name = v.blk.20.ln1.weight, tensor_size=4608, offset=755819264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[350]: n_dims = 1, name = v.blk.20.ln1.bias, tensor_size=4608, offset=755823872, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[351]: n_dims = 2, name = v.blk.20.ffn_down.weight, tensor_size=9916416, offset=755828480, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[352]: n_dims = 1, name = v.blk.20.ffn_down.bias, tensor_size=17216, offset=765744896, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[353]: n_dims = 2, name = v.blk.20.ffn_up.weight, tensor_size=9916416, offset=765762112, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[354]: n_dims = 1, name = v.blk.20.ffn_up.bias, tensor_size=4608, offset=775678528, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[355]: n_dims = 1, name = v.blk.20.ln2.weight, tensor_size=4608, offset=775683136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[356]: n_dims = 1, name = v.blk.20.ln2.bias, tensor_size=4608, offset=775687744, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[357]: n_dims = 2, name = v.blk.21.attn_k.weight, tensor_size=2654208, offset=775692352, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[358]: n_dims = 1, name = v.blk.21.attn_k.bias, tensor_size=4608, offset=778346560, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[359]: n_dims = 2, name = v.blk.21.attn_v.weight, tensor_size=2654208, offset=778351168, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[360]: n_dims = 1, name = v.blk.21.attn_v.bias, tensor_size=4608, offset=781005376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[361]: n_dims = 2, name = v.blk.21.attn_q.weight, tensor_size=2654208, offset=781009984, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[362]: n_dims = 1, name = v.blk.21.attn_q.bias, tensor_size=4608, offset=783664192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[363]: n_dims = 2, name = v.blk.21.attn_out.weight, tensor_size=2654208, offset=783668800, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[364]: n_dims = 1, name = v.blk.21.attn_out.bias, tensor_size=4608, offset=786323008, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[365]: n_dims = 1, name = v.blk.21.ln1.weight, tensor_size=4608, offset=786327616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[366]: n_dims = 1, name = v.blk.21.ln1.bias, tensor_size=4608, offset=786332224, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[367]: n_dims = 2, name = v.blk.21.ffn_down.weight, tensor_size=9916416, offset=786336832, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[368]: n_dims = 1, name = v.blk.21.ffn_down.bias, tensor_size=17216, offset=796253248, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[369]: n_dims = 2, name = v.blk.21.ffn_up.weight, tensor_size=9916416, offset=796270464, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[370]: n_dims = 1, name = v.blk.21.ffn_up.bias, tensor_size=4608, offset=806186880, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[371]: n_dims = 1, name = v.blk.21.ln2.weight, tensor_size=4608, offset=806191488, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[372]: n_dims = 1, name = v.blk.21.ln2.bias, tensor_size=4608, offset=806196096, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[373]: n_dims = 2, name = v.blk.22.attn_k.weight, tensor_size=2654208, offset=806200704, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[374]: n_dims = 1, name = v.blk.22.attn_k.bias, tensor_size=4608, offset=808854912, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[375]: n_dims = 2, name = v.blk.22.attn_v.weight, tensor_size=2654208, offset=808859520, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[376]: n_dims = 1, name = v.blk.22.attn_v.bias, tensor_size=4608, offset=811513728, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[377]: n_dims = 2, name = v.blk.22.attn_q.weight, tensor_size=2654208, offset=811518336, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[378]: n_dims = 1, name = v.blk.22.attn_q.bias, tensor_size=4608, offset=814172544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[379]: n_dims = 2, name = v.blk.22.attn_out.weight, tensor_size=2654208, offset=814177152, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[380]: n_dims = 1, name = v.blk.22.attn_out.bias, tensor_size=4608, offset=816831360, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[381]: n_dims = 1, name = v.blk.22.ln1.weight, tensor_size=4608, offset=816835968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[382]: n_dims = 1, name = v.blk.22.ln1.bias, tensor_size=4608, offset=816840576, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[383]: n_dims = 2, name = v.blk.22.ffn_down.weight, tensor_size=9916416, offset=816845184, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[384]: n_dims = 1, name = v.blk.22.ffn_down.bias, tensor_size=17216, offset=826761600, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[385]: n_dims = 2, name = v.blk.22.ffn_up.weight, tensor_size=9916416, offset=826778816, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[386]: n_dims = 1, name = v.blk.22.ffn_up.bias, tensor_size=4608, offset=836695232, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[387]: n_dims = 1, name = v.blk.22.ln2.weight, tensor_size=4608, offset=836699840, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[388]: n_dims = 1, name = v.blk.22.ln2.bias, tensor_size=4608, offset=836704448, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[389]: n_dims = 2, name = v.blk.23.attn_k.weight, tensor_size=2654208, offset=836709056, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[390]: n_dims = 1, name = v.blk.23.attn_k.bias, tensor_size=4608, offset=839363264, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[391]: n_dims = 2, name = v.blk.23.attn_v.weight, tensor_size=2654208, offset=839367872, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[392]: n_dims = 1, name = v.blk.23.attn_v.bias, tensor_size=4608, offset=842022080, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[393]: n_dims = 2, name = v.blk.23.attn_q.weight, tensor_size=2654208, offset=842026688, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[394]: n_dims = 1, name = v.blk.23.attn_q.bias, tensor_size=4608, offset=844680896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[395]: n_dims = 2, name = v.blk.23.attn_out.weight, tensor_size=2654208, offset=844685504, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[396]: n_dims = 1, name = v.blk.23.attn_out.bias, tensor_size=4608, offset=847339712, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[397]: n_dims = 1, name = v.blk.23.ln1.weight, tensor_size=4608, offset=847344320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[398]: n_dims = 1, name = v.blk.23.ln1.bias, tensor_size=4608, offset=847348928, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[399]: n_dims = 2, name = v.blk.23.ffn_down.weight, tensor_size=9916416, offset=847353536, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[400]: n_dims = 1, name = v.blk.23.ffn_down.bias, tensor_size=17216, offset=857269952, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[401]: n_dims = 2, name = v.blk.23.ffn_up.weight, tensor_size=9916416, offset=857287168, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[402]: n_dims = 1, name = v.blk.23.ffn_up.bias, tensor_size=4608, offset=867203584, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[403]: n_dims = 1, name = v.blk.23.ln2.weight, tensor_size=4608, offset=867208192, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[404]: n_dims = 1, name = v.blk.23.ln2.bias, tensor_size=4608, offset=867212800, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[405]: n_dims = 2, name = v.blk.24.attn_k.weight, tensor_size=2654208, offset=867217408, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[406]: n_dims = 1, name = v.blk.24.attn_k.bias, tensor_size=4608, offset=869871616, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[407]: n_dims = 2, name = v.blk.24.attn_v.weight, tensor_size=2654208, offset=869876224, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[408]: n_dims = 1, name = v.blk.24.attn_v.bias, tensor_size=4608, offset=872530432, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[409]: n_dims = 2, name = v.blk.24.attn_q.weight, tensor_size=2654208, offset=872535040, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[410]: n_dims = 1, name = v.blk.24.attn_q.bias, tensor_size=4608, offset=875189248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[411]: n_dims = 2, name = v.blk.24.attn_out.weight, tensor_size=2654208, offset=875193856, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[412]: n_dims = 1, name = v.blk.24.attn_out.bias, tensor_size=4608, offset=877848064, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[413]: n_dims = 1, name = v.blk.24.ln1.weight, tensor_size=4608, offset=877852672, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[414]: n_dims = 1, name = v.blk.24.ln1.bias, tensor_size=4608, offset=877857280, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[415]: n_dims = 2, name = v.blk.24.ffn_down.weight, tensor_size=9916416, offset=877861888, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[416]: n_dims = 1, name = v.blk.24.ffn_down.bias, tensor_size=17216, offset=887778304, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[417]: n_dims = 2, name = v.blk.24.ffn_up.weight, tensor_size=9916416, offset=887795520, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[418]: n_dims = 1, name = v.blk.24.ffn_up.bias, tensor_size=4608, offset=897711936, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[419]: n_dims = 1, name = v.blk.24.ln2.weight, tensor_size=4608, offset=897716544, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[420]: n_dims = 1, name = v.blk.24.ln2.bias, tensor_size=4608, offset=897721152, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[421]: n_dims = 2, name = v.blk.25.attn_k.weight, tensor_size=2654208, offset=897725760, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[422]: n_dims = 1, name = v.blk.25.attn_k.bias, tensor_size=4608, offset=900379968, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[423]: n_dims = 2, name = v.blk.25.attn_v.weight, tensor_size=2654208, offset=900384576, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[424]: n_dims = 1, name = v.blk.25.attn_v.bias, tensor_size=4608, offset=903038784, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[425]: n_dims = 2, name = v.blk.25.attn_q.weight, tensor_size=2654208, offset=903043392, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[426]: n_dims = 1, name = v.blk.25.attn_q.bias, tensor_size=4608, offset=905697600, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[427]: n_dims = 2, name = v.blk.25.attn_out.weight, tensor_size=2654208, offset=905702208, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[428]: n_dims = 1, name = v.blk.25.attn_out.bias, tensor_size=4608, offset=908356416, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[429]: n_dims = 1, name = v.blk.25.ln1.weight, tensor_size=4608, offset=908361024, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[430]: n_dims = 1, name = v.blk.25.ln1.bias, tensor_size=4608, offset=908365632, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[431]: n_dims = 2, name = v.blk.25.ffn_down.weight, tensor_size=9916416, offset=908370240, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[432]: n_dims = 1, name = v.blk.25.ffn_down.bias, tensor_size=17216, offset=918286656, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[433]: n_dims = 2, name = v.blk.25.ffn_up.weight, tensor_size=9916416, offset=918303872, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[434]: n_dims = 1, name = v.blk.25.ffn_up.bias, tensor_size=4608, offset=928220288, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[435]: n_dims = 1, name = v.blk.25.ln2.weight, tensor_size=4608, offset=928224896, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[436]: n_dims = 1, name = v.blk.25.ln2.bias, tensor_size=4608, offset=928229504, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[437]: n_dims = 2, name = v.blk.26.attn_k.weight, tensor_size=2654208, offset=928234112, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[438]: n_dims = 1, name = v.blk.26.attn_k.bias, tensor_size=4608, offset=930888320, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[439]: n_dims = 2, name = v.blk.26.attn_v.weight, tensor_size=2654208, offset=930892928, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[440]: n_dims = 1, name = v.blk.26.attn_v.bias, tensor_size=4608, offset=933547136, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[441]: n_dims = 2, name = v.blk.26.attn_q.weight, tensor_size=2654208, offset=933551744, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[442]: n_dims = 1, name = v.blk.26.attn_q.bias, tensor_size=4608, offset=936205952, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[443]: n_dims = 2, name = v.blk.26.attn_out.weight, tensor_size=2654208, offset=936210560, shape:[1152, 1152, 1, 1], type = f16 clip_model_loader: tensor[444]: n_dims = 1, name = v.blk.26.attn_out.bias, tensor_size=4608, offset=938864768, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=938869376, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=938873984, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=938878592, shape:[1152, 4304, 1, 1], type = f16 clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=948795008, shape:[4304, 1, 1, 1], type = f32 clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=948812224, shape:[4304, 1152, 1, 1], type = f16 clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=958728640, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=958733248, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=958737856, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=958742464, shape:[1152, 1, 1, 1], type = f32 clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=958747072, shape:[1152, 1, 1, 1], type = f32 load_hparams: projector: resampler load_hparams: n_embd: 1152 load_hparams: n_head: 16 load_hparams: n_ff: 4304 load_hparams: n_layer: 27 load_hparams: projection_dim: 0 load_hparams: image_size: 448 load_hparams: patch_size: 14 load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 5 load_hparams: proj_scale_factor: 0 load_hparams: n_wa_pattern: 0 load_hparams: ffn_op: gelu load_hparams: model size: 914.34 MiB load_hparams: metadata size: 0.16 MiB load_tensors: loaded 455 tensors from E:\AI\Ollama\blobs\sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761 clip.cpp:3782: Unknown minicpmv version time=2025-08-11T21:16:07.316+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" time=2025-08-11T21:16:07.566+03:00 level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409" [GIN] 2025/08/11 - 21:16:07 | 500 | 5.4620974s | 127.0.0.1 | POST "/api/chat" time=2025-08-11T21:16:12.601+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0309275 runner.size="3.8 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=26968 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b time=2025-08-11T21:16:12.848+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2811761 runner.size="3.8 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=26968 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b time=2025-08-11T21:16:13.098+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5313937 runner.size="3.8 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=26968 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
GiteaMirror commented 2026-05-04 19:37:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2025):

clip.cpp:3782: Unknown minicpmv version

https://github.com/ollama/ollama/issues/11730

<!-- gh-comment-id:3176746043 --> @rick-github commented on GitHub (Aug 11, 2025): ``` clip.cpp:3782: Unknown minicpmv version ``` https://github.com/ollama/ollama/issues/11730
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
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
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#69863
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?