github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4076] MoonDream:Latest Not Working #28291

New Issue
Closed
opened 2026-04-22 06:17:28 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 06:17:28 -05:00
Owner
Copy Link

Originally created by @rb81 on GitHub (May 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4076

What is the issue?

When running moondream:latest, the following error message is received:

Error: llama runner process no longer running: -1

Tried running the model from CLI using ollama serve as well as the desktop application.
Tried using the model form CLI as well as Open-WebUI. Same result for both.

(Maybe related to: https://github.com/ollama/ollama/issues/4063)

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.32

Originally created by @rb81 on GitHub (May 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4076 ### What is the issue? When running moondream:latest, the following error message is received: ``` Error: llama runner process no longer running: -1 ``` Tried running the model from CLI using `ollama serve` as well as the desktop application. Tried using the model form CLI as well as Open-WebUI. Same result for both. (Maybe related to: https://github.com/ollama/ollama/issues/4063) ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-22 06:17:28 -05:00
GiteaMirror commented 2026-04-22 06:17:31 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (May 1, 2024):

@rb81 Sorry about this. Moondream only works on 0.1.33 (pre-release) or later. We shouldn't have published before supporting it. Apologies.

<!-- gh-comment-id:2088877082 --> @mchiang0610 commented on GitHub (May 1, 2024): @rb81 Sorry about this. Moondream only works on 0.1.33 (pre-release) or later. We shouldn't have published before supporting it. Apologies.
GiteaMirror commented 2026-04-22 06:17:32 -05:00
Author
Owner
Copy Link

@omarnahdi commented on GitHub (Oct 30, 2024):

@mchiang0610 When can we expect this to work? because I still can't use this model yet and it doesn't even work with LM studio too.

<!-- gh-comment-id:2447509549 --> @omarnahdi commented on GitHub (Oct 30, 2024): @mchiang0610 When can we expect this to work? because I still can't use this model yet and it doesn't even work with LM studio too.
GiteaMirror commented 2026-04-22 06:17:33 -05:00
Author
Owner
Copy Link

@maxi1134 commented on GitHub (Feb 13, 2025):

@mchiang0610 When can we expect this to work? because I still can't use this model yet and it doesn't even work with LM studio too.

This is still an issue for me using this addon: https://github.com/valentinfrlch/ha-llmvision within HA.

Ollama logs show this:

02b (version GGUF V3 (latest))
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   0:                       general.architecture str              = phi2
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   1:                               general.name str              = moondream2
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   2:                        phi2.context_length u32              = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   3:                      phi2.embedding_length u32              = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   4:                   phi2.feed_forward_length u32              = 8192
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   5:                           phi2.block_count u32              = 24
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   6:                  phi2.attention.head_count u32              = 32
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   7:               phi2.attention.head_count_kv u32              = 32
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   8:          phi2.attention.layer_norm_epsilon f32              = 0.000010
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv   9:                  phi2.rope.dimension_count u32              = 32
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  10:                          general.file_type u32              = 2
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  11:               tokenizer.ggml.add_bos_token bool             = false
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = gpt2
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,51200]   = ["!", "\"", "#", "$", "%", "&", "'", ...
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,51200]   = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,50000]   = ["Ġ t", "Ġ a", "h e", "i n", "r e",...
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 50256
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 50256
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 50256
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv  19:               general.quantization_version u32              = 2
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - type  f32:  147 tensors
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - type q4_0:   97 tensors
Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - type q6_K:    1 tensors
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_vocab: special tokens cache size = 944
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_vocab: token to piece cache size = 0.3151 MB
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: format           = GGUF V3 (latest)
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: arch             = phi2
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: vocab type       = BPE
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_vocab          = 51200
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_merges         = 50000
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: vocab_only       = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_ctx_train      = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd           = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_layer          = 24
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_head           = 32
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_head_kv        = 32
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_rot            = 32
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_swa            = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_head_k    = 64
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_head_v    = 64
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_gqa            = 1
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_k_gqa     = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_v_gqa     = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_norm_eps       = 1.0e-05
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_norm_rms_eps   = 0.0e+00
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_clamp_kqv      = 0.0e+00
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_logit_scale    = 0.0e+00
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_ff             = 8192
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_expert         = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_expert_used    = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: causal attn      = 1
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: pooling type     = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: rope type        = 2
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: rope scaling     = linear
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: freq_base_train  = 10000.0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: freq_scale_train = 1
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_ctx_orig_yarn  = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: rope_finetuned   = unknown
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_d_conv       = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_d_inner      = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_d_state      = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_dt_rank      = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_dt_b_c_rms   = 0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model type       = 1B
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model ftype      = Q4_0
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model params     = 1.42 B
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model size       = 788.55 MiB (4.66 BPW)
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: general.name     = moondream2
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: BOS token        = 50256 '<|endoftext|>'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: EOS token        = 50256 '<|endoftext|>'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: UNK token        = 50256 '<|endoftext|>'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: LF token         = 128 'Ä'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: EOT token        = 50256 '<|endoftext|>'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: EOG token        = 50256 '<|endoftext|>'
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: max token length = 256
Feb 13 14:15:32 machinelearning ollama[854992]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Feb 13 14:15:32 machinelearning ollama[854992]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Feb 13 14:15:32 machinelearning ollama[854992]: ggml_cuda_init: found 1 CUDA devices:
Feb 13 14:15:32 machinelearning ollama[854992]:   Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Feb 13 14:15:32 machinelearning ollama[854992]: time=2025-02-13T14:15:32.712Z level=INFO source=server.go:610 msg="waiting for server to become available" status="llm server loading model"
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: ggml ctx size =    0.22 MiB
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: offloading 24 repeating layers to GPU
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: offloading non-repeating layers to GPU
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: offloaded 25/25 layers to GPU
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors:        CPU buffer size =    56.25 MiB
Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors:      CUDA0 buffer size =   732.30 MiB
Feb 13 14:15:32 machinelearning ollama[854992]: time=2025-02-13T14:15:32.963Z level=DEBUG source=server.go:621 msg="model load progress 1.00"
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: n_ctx      = 8192
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: n_batch    = 2048
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: n_ubatch   = 512
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: flash_attn = 1
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: freq_base  = 10000.0
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: freq_scale = 1
Feb 13 14:15:32 machinelearning ollama[854992]: llama_kv_cache_init:      CUDA0 KV buffer size =   816.00 MiB
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: KV self size  =  816.00 MiB, K (q8_0):  408.00 MiB, V (q8_0):  408.00 MiB
Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model:  CUDA_Host  output buffer size =     0.81 MiB
Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model:      CUDA0 compute buffer size =   108.00 MiB
Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model:  CUDA_Host compute buffer size =    50.01 MiB
Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model: graph nodes  = 826
Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model: graph splits = 50
Feb 13 14:15:33 machinelearning ollama[854992]: key clip.vision.image_grid_pinpoints not found in file
Feb 13 14:15:33 machinelearning ollama[854992]: key clip.vision.mm_patch_merge_type not found in file
Feb 13 14:15:33 machinelearning ollama[854992]: key clip.vision.image_crop_resolution not found in file
Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.213Z level=INFO source=server.go:615 msg="llama runner started in 0.75 seconds"
Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.213Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b
Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.214Z level=DEBUG source=server.go:986 msg="new runner detected, loading model for cgo tokenization"
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: loaded meta data with 20 key-value pairs and 245 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b (version GGUF V3 (latest))
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   0:                       general.architecture str              = phi2
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   1:                               general.name str              = moondream2
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   2:                        phi2.context_length u32              = 2048
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   3:                      phi2.embedding_length u32              = 2048
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   4:                   phi2.feed_forward_length u32              = 8192
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   5:                           phi2.block_count u32              = 24
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   6:                  phi2.attention.head_count u32              = 32
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   7:               phi2.attention.head_count_kv u32              = 32
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   8:          phi2.attention.layer_norm_epsilon f32              = 0.000010
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv   9:                  phi2.rope.dimension_count u32              = 32
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  10:                          general.file_type u32              = 2
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  11:               tokenizer.ggml.add_bos_token bool             = false
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = gpt2
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,51200]   = ["!", "\"", "#", "$", "%", "&", "'", ...
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,51200]   = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,50000]   = ["Ġ t", "Ġ a", "h e", "i n", "r e",...
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 50256
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 50256
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 50256
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv  19:               general.quantization_version u32              = 2
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - type  f32:  147 tensors
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - type q4_0:   97 tensors
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - type q6_K:    1 tensors
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_vocab: special tokens cache size = 944
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_vocab: token to piece cache size = 0.3151 MB
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: format           = GGUF V3 (latest)
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: arch             = phi2
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: vocab type       = BPE
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: n_vocab          = 51200
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: n_merges         = 50000
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: vocab_only       = 1
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model type       = ?B
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model ftype      = all F32
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model params     = 1.42 B
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model size       = 788.55 MiB (4.66 BPW)
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: general.name     = moondream2
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: BOS token        = 50256 '<|endoftext|>'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: EOS token        = 50256 '<|endoftext|>'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: UNK token        = 50256 '<|endoftext|>'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: LF token         = 128 'Ä'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: EOT token        = 50256 '<|endoftext|>'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: EOG token        = 50256 '<|endoftext|>'
Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: max token length = 256
Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_load: vocab only - skipping tensors
Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.375Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: "
Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.559Z level=DEBUG source=image.go:179 msg="storing image embeddings in cache" entry=0 used=0001-01-01T00:00:00.000Z
Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.559Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=750 used=0 remaining=750
Feb 13 14:15:35 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:15:35 | 200 |  4.035247075s |    192.168.0.15 | POST     "/api/chat"
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.797Z level=DEBUG source=sched.go:466 msg="context for request finished"
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.797Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.797Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.805Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.805Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: "
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.806Z level=DEBUG source=image.go:154 msg="loading image embeddings from cache" entry=0
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.807Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=750 prompt=750 used=749 remaining=1
Feb 13 14:15:35 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:15:35 | 200 |   38.439839ms |    192.168.0.15 | POST     "/api/chat"
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.837Z level=DEBUG source=sched.go:407 msg="context for request finished"
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.837Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s
Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.837Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0
Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.076Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b
Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.077Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: "
Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.158Z level=DEBUG source=image.go:179 msg="storing image embeddings in cache" entry=1 used=0001-01-01T00:00:00.000Z
Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.158Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=750 prompt=750 used=3 remaining=747
Feb 13 14:16:02 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:16:02 | 200 |  2.322392762s |    192.168.0.15 | POST     "/api/chat"
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.392Z level=DEBUG source=sched.go:407 msg="context for request finished"
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.392Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.392Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.525Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.526Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: "
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.527Z level=DEBUG source=image.go:154 msg="loading image embeddings from cache" entry=1
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.527Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=750 prompt=750 used=749 remaining=1
Feb 13 14:16:02 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:16:02 | 200 |    44.72938ms |    192.168.0.15 | POST     "/api/chat"
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.564Z level=DEBUG source=sched.go:407 msg="context for request finished"
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.564Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s
Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.564Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0
<!-- gh-comment-id:2656745091 --> @maxi1134 commented on GitHub (Feb 13, 2025): > [@mchiang0610](https://github.com/mchiang0610) When can we expect this to work? because I still can't use this model yet and it doesn't even work with LM studio too. This is still an issue for me using this addon: https://github.com/valentinfrlch/ha-llmvision within HA. Ollama logs show this: ``` 02b (version GGUF V3 (latest)) Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 0: general.architecture str = phi2 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 1: general.name str = moondream2 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 2: phi2.context_length u32 = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 3: phi2.embedding_length u32 = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 4: phi2.feed_forward_length u32 = 8192 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 5: phi2.block_count u32 = 24 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 6: phi2.attention.head_count u32 = 32 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 7: phi2.attention.head_count_kv u32 = 32 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 8: phi2.attention.layer_norm_epsilon f32 = 0.000010 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 9: phi2.rope.dimension_count u32 = 32 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 10: general.file_type u32 = 2 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 12: tokenizer.ggml.model str = gpt2 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,51200] = ["!", "\"", "#", "$", "%", "&", "'", ... Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,51200] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,50000] = ["Ġ t", "Ġ a", "h e", "i n", "r e",... Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 50256 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 50256 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 50256 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - kv 19: general.quantization_version u32 = 2 Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - type f32: 147 tensors Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - type q4_0: 97 tensors Feb 13 14:15:32 machinelearning ollama[854992]: llama_model_loader: - type q6_K: 1 tensors Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_vocab: special tokens cache size = 944 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_vocab: token to piece cache size = 0.3151 MB Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: format = GGUF V3 (latest) Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: arch = phi2 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: vocab type = BPE Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_vocab = 51200 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_merges = 50000 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: vocab_only = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_ctx_train = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_layer = 24 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_head = 32 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_head_kv = 32 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_rot = 32 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_swa = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_head_k = 64 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_head_v = 64 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_gqa = 1 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_k_gqa = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_embd_v_gqa = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_norm_eps = 1.0e-05 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_norm_rms_eps = 0.0e+00 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_clamp_kqv = 0.0e+00 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: f_logit_scale = 0.0e+00 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_ff = 8192 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_expert = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_expert_used = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: causal attn = 1 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: pooling type = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: rope type = 2 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: rope scaling = linear Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: freq_base_train = 10000.0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: freq_scale_train = 1 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: n_ctx_orig_yarn = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: rope_finetuned = unknown Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_d_conv = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_d_inner = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_d_state = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_dt_rank = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: ssm_dt_b_c_rms = 0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model type = 1B Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model ftype = Q4_0 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model params = 1.42 B Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: model size = 788.55 MiB (4.66 BPW) Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: general.name = moondream2 Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: BOS token = 50256 '<|endoftext|>' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: EOS token = 50256 '<|endoftext|>' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: UNK token = 50256 '<|endoftext|>' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: LF token = 128 'Ä' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: EOT token = 50256 '<|endoftext|>' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: EOG token = 50256 '<|endoftext|>' Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_print_meta: max token length = 256 Feb 13 14:15:32 machinelearning ollama[854992]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Feb 13 14:15:32 machinelearning ollama[854992]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Feb 13 14:15:32 machinelearning ollama[854992]: ggml_cuda_init: found 1 CUDA devices: Feb 13 14:15:32 machinelearning ollama[854992]: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes Feb 13 14:15:32 machinelearning ollama[854992]: time=2025-02-13T14:15:32.712Z level=INFO source=server.go:610 msg="waiting for server to become available" status="llm server loading model" Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: ggml ctx size = 0.22 MiB Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: offloading 24 repeating layers to GPU Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: offloading non-repeating layers to GPU Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: offloaded 25/25 layers to GPU Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: CPU buffer size = 56.25 MiB Feb 13 14:15:32 machinelearning ollama[854992]: llm_load_tensors: CUDA0 buffer size = 732.30 MiB Feb 13 14:15:32 machinelearning ollama[854992]: time=2025-02-13T14:15:32.963Z level=DEBUG source=server.go:621 msg="model load progress 1.00" Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: n_ctx = 8192 Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: n_batch = 2048 Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: n_ubatch = 512 Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: flash_attn = 1 Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: freq_base = 10000.0 Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: freq_scale = 1 Feb 13 14:15:32 machinelearning ollama[854992]: llama_kv_cache_init: CUDA0 KV buffer size = 816.00 MiB Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: KV self size = 816.00 MiB, K (q8_0): 408.00 MiB, V (q8_0): 408.00 MiB Feb 13 14:15:32 machinelearning ollama[854992]: llama_new_context_with_model: CUDA_Host output buffer size = 0.81 MiB Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model: CUDA0 compute buffer size = 108.00 MiB Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model: CUDA_Host compute buffer size = 50.01 MiB Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model: graph nodes = 826 Feb 13 14:15:33 machinelearning ollama[854992]: llama_new_context_with_model: graph splits = 50 Feb 13 14:15:33 machinelearning ollama[854992]: key clip.vision.image_grid_pinpoints not found in file Feb 13 14:15:33 machinelearning ollama[854992]: key clip.vision.mm_patch_merge_type not found in file Feb 13 14:15:33 machinelearning ollama[854992]: key clip.vision.image_crop_resolution not found in file Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.213Z level=INFO source=server.go:615 msg="llama runner started in 0.75 seconds" Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.213Z level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.214Z level=DEBUG source=server.go:986 msg="new runner detected, loading model for cgo tokenization" Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: loaded meta data with 20 key-value pairs and 245 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b (version GGUF V3 (latest)) Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 0: general.architecture str = phi2 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 1: general.name str = moondream2 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 2: phi2.context_length u32 = 2048 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 3: phi2.embedding_length u32 = 2048 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 4: phi2.feed_forward_length u32 = 8192 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 5: phi2.block_count u32 = 24 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 6: phi2.attention.head_count u32 = 32 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 7: phi2.attention.head_count_kv u32 = 32 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 8: phi2.attention.layer_norm_epsilon f32 = 0.000010 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 9: phi2.rope.dimension_count u32 = 32 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 10: general.file_type u32 = 2 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 12: tokenizer.ggml.model str = gpt2 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,51200] = ["!", "\"", "#", "$", "%", "&", "'", ... Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,51200] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,50000] = ["Ġ t", "Ġ a", "h e", "i n", "r e",... Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 50256 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 50256 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 50256 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - kv 19: general.quantization_version u32 = 2 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - type f32: 147 tensors Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - type q4_0: 97 tensors Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_loader: - type q6_K: 1 tensors Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_vocab: missing or unrecognized pre-tokenizer type, using: 'default' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_vocab: special tokens cache size = 944 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_vocab: token to piece cache size = 0.3151 MB Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: format = GGUF V3 (latest) Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: arch = phi2 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: vocab type = BPE Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: n_vocab = 51200 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: n_merges = 50000 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: vocab_only = 1 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model type = ?B Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model ftype = all F32 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model params = 1.42 B Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: model size = 788.55 MiB (4.66 BPW) Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: general.name = moondream2 Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: BOS token = 50256 '<|endoftext|>' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: EOS token = 50256 '<|endoftext|>' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: UNK token = 50256 '<|endoftext|>' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: LF token = 128 'Ä' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: EOT token = 50256 '<|endoftext|>' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: EOG token = 50256 '<|endoftext|>' Feb 13 14:15:33 machinelearning ollama[854992]: llm_load_print_meta: max token length = 256 Feb 13 14:15:33 machinelearning ollama[854992]: llama_model_load: vocab only - skipping tensors Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.375Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: " Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.559Z level=DEBUG source=image.go:179 msg="storing image embeddings in cache" entry=0 used=0001-01-01T00:00:00.000Z Feb 13 14:15:33 machinelearning ollama[854992]: time=2025-02-13T14:15:33.559Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=750 used=0 remaining=750 Feb 13 14:15:35 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:15:35 | 200 | 4.035247075s | 192.168.0.15 | POST "/api/chat" Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.797Z level=DEBUG source=sched.go:466 msg="context for request finished" Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.797Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.797Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0 Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.805Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.805Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: " Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.806Z level=DEBUG source=image.go:154 msg="loading image embeddings from cache" entry=0 Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.807Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=750 prompt=750 used=749 remaining=1 Feb 13 14:15:35 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:15:35 | 200 | 38.439839ms | 192.168.0.15 | POST "/api/chat" Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.837Z level=DEBUG source=sched.go:407 msg="context for request finished" Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.837Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s Feb 13 14:15:35 machinelearning ollama[854992]: time=2025-02-13T14:15:35.837Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0 Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.076Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.077Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: " Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.158Z level=DEBUG source=image.go:179 msg="storing image embeddings in cache" entry=1 used=0001-01-01T00:00:00.000Z Feb 13 14:16:00 machinelearning ollama[854992]: time=2025-02-13T14:16:00.158Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=750 prompt=750 used=3 remaining=747 Feb 13 14:16:02 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:16:02 | 200 | 2.322392762s | 192.168.0.15 | POST "/api/chat" Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.392Z level=DEBUG source=sched.go:407 msg="context for request finished" Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.392Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.392Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0 Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.525Z level=DEBUG source=sched.go:575 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.526Z level=DEBUG source=routes.go:1464 msg="chat request" images=1 prompt=" Question: [img-0] Image 1:\n\nIs there snow present on this image?\n\n Answer: " Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.527Z level=DEBUG source=image.go:154 msg="loading image embeddings from cache" entry=1 Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.527Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=750 prompt=750 used=749 remaining=1 Feb 13 14:16:02 machinelearning ollama[854992]: [GIN] 2025/02/13 - 14:16:02 | 200 | 44.72938ms | 192.168.0.15 | POST "/api/chat" Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.564Z level=DEBUG source=sched.go:407 msg="context for request finished" Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.564Z level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b duration=5m0s Feb 13 14:16:02 machinelearning ollama[854992]: time=2025-02-13T14:16:02.564Z level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/usr/share/ollama/.ollama/models/blobs/sha256-e554c6b9de016673fd2c732e0342967727e9659ca5f853a4947cc96263fa602b refCount=0 ```
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#28291
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?