[GH-ISSUE #9639] Unsupported Value NaN in Ollama log #32050

New Issue

Open

opened 2026-04-22 12:55:42 -05:00 by GiteaMirror · 34 comments

GiteaMirror commented 2026-04-22 12:55:42 -05:00

Owner

Copy Link

Originally created by @satya-devloper on GitHub (Mar 11, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9639

Originally assigned to: @mxyng on GitHub.

What is the issue?

llama_model_load: vocab only - skipping tensors
time=2025-03-11T09:41:09.612+05:30 level=DEBUG source=runner.go:741 msg="embedding request" content="{"TASKNAME": "Task1", "STATUS": "FAILED", "SPACE": "spac1", "STARTED TIMESTAMP": "2025-02-20T08:38:12.046Z", "FAILED ISSUE": "No Issue Mentioned", "FAILED DETAILS": "No Details Found", "RESOLUTION STEP": " 'steps'", "TASK COMPLETION DURATION": "5738.378999948502"}"
time=2025-03-11T09:41:09.752+05:30 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=315 used=0 remaining=315
time=2025-03-11T09:41:42.948+05:30 level=INFO source=server.go:915 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"

To Replicate:
curl -s localhost:11434/api/embed -d '{"model":"nomic-embed-text","input":["Why is the sky blue?","why is the grass green"]}' | jq '.embeddings=[.embeddings[]|length]'

simply trying this curl is also giving same response: unsupported value: NaN

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

0.5.11

Originally created by @satya-devloper on GitHub (Mar 11, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9639 Originally assigned to: @mxyng on GitHub. ### What is the issue? llama_model_load: vocab only - skipping tensors time=2025-03-11T09:41:09.612+05:30 level=DEBUG source=runner.go:741 msg="embedding request" content="{\"TASKNAME\": \"Task1\", \"STATUS\": \"FAILED\", \"SPACE\": \"spac1\", \"STARTED TIMESTAMP\": \"2025-02-20T08:38:12.046Z\", \"FAILED ISSUE\": \"No Issue Mentioned\", \"FAILED DETAILS\": \"No Details Found\", \"RESOLUTION STEP\": \" 'steps'\", \"TASK COMPLETION DURATION\": \"5738.378999948502\"}" time=2025-03-11T09:41:09.752+05:30 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=315 used=0 remaining=315 time=2025-03-11T09:41:42.948+05:30 level=INFO source=server.go:915 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" To Replicate: curl -s localhost:11434/api/embed -d '{"model":"nomic-embed-text","input":["Why is the sky blue?","why is the grass green"]}' | jq '.embeddings=[.embeddings[]|length]' simply trying this curl is also giving same response: unsupported value: NaN ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.5.11

GiteaMirror added the bug label 2026-04-22 12:55:42 -05:00

GiteaMirror commented 2026-04-22 12:55:44 -05:00

Author

Owner

Copy Link

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

$ ollama -v
ollama version is 0.5.11
$ curl -s localhost:11434/api/embed -d '{"model":"nomic-embed-text","input":["Why is the sky blue?","why is the grass green"]}' | jq '.embeddings=[.embeddings[]|length]'
{
  "model": "nomic-embed-text",
  "embeddings": [
    768,
    768
  ],
  "total_duration": 3523221001,
  "load_duration": 3307812718,
  "prompt_eval_count": 11
}
$ curl -s localhost:11434/api/embed -d '{"model":"nomic-embed-text","input":["{\"TASKNAME\": \"Task1\", \"STATUS\": \"FAILED\", \"SPACE\": \"spac1\", \"STARTED TIMESTAMP\": \"2025-02-20T08:38:12.046Z\", \"FAILED ISSUE\": \"No Issue Mentioned\", \"FAILED DETAILS\": \"No Details Found\", \"RESOLUTION STEP\": \" '"'"'steps'"'"'\", \"TASK COMPLETION DURATION\": \"5738.378999948502\"}"]}' | jq '.embeddings=[.embeddings[]|length]'
{
  "model": "nomic-embed-text",
  "embeddings": [
    768
  ],
  "total_duration": 420772216,
  "load_duration": 395957210,
  "prompt_eval_count": 110
}

A full server log may aid in debugging.

<!-- gh-comment-id:2713188193 --> @rick-github commented on GitHub (Mar 11, 2025): ```console $ ollama -v ollama version is 0.5.11 $ curl -s localhost:11434/api/embed -d '{"model":"nomic-embed-text","input":["Why is the sky blue?","why is the grass green"]}' | jq '.embeddings=[.embeddings[]|length]' { "model": "nomic-embed-text", "embeddings": [ 768, 768 ], "total_duration": 3523221001, "load_duration": 3307812718, "prompt_eval_count": 11 } $ curl -s localhost:11434/api/embed -d '{"model":"nomic-embed-text","input":["{\"TASKNAME\": \"Task1\", \"STATUS\": \"FAILED\", \"SPACE\": \"spac1\", \"STARTED TIMESTAMP\": \"2025-02-20T08:38:12.046Z\", \"FAILED ISSUE\": \"No Issue Mentioned\", \"FAILED DETAILS\": \"No Details Found\", \"RESOLUTION STEP\": \" '"'"'steps'"'"'\", \"TASK COMPLETION DURATION\": \"5738.378999948502\"}"]}' | jq '.embeddings=[.embeddings[]|length]' { "model": "nomic-embed-text", "embeddings": [ 768 ], "total_duration": 420772216, "load_duration": 395957210, "prompt_eval_count": 110 } ``` A full server log may aid in debugging.

GiteaMirror commented 2026-04-22 12:55:44 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 12, 2025):

time=2025-03-12T10:13:06.067+05:30 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="14.7 GiB" before.free="4.5 GiB" before.free_swap="2.0 GiB" now.total="14.7 GiB" now.free="4.5 GiB" now.free_swap="2.0 GiB"
time=2025-03-12T10:13:06.067+05:30 level=DEBUG source=sched.go:181 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=0x55cc821a7b40 gpu_count=1
time=2025-03-12T10:13:06.167+05:30 level=DEBUG source=sched.go:211 msg="cpu mode with first model, loading"
time=2025-03-12T10:13:06.188+05:30 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="14.7 GiB" before.free="4.5 GiB" before.free_swap="2.0 GiB" now.total="14.7 GiB" now.free="4.5 GiB" now.free_swap="2.0 GiB"
time=2025-03-12T10:13:06.188+05:30 level=INFO source=server.go:100 msg="system memory" total="14.7 GiB" free="4.5 GiB" free_swap="2.0 GiB"
time=2025-03-12T10:13:06.198+05:30 level=DEBUG source=memory.go:107 msg=evaluating library=cpu gpu_count=1 available="[4.5 GiB]"
time=2025-03-12T10:13:06.199+05:30 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=13 layers.offload=0 layers.split="" memory.available="[4.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="352.9 MiB" memory.required.partial="0 B" memory.required.kv="24.0 MiB" memory.required.allocations="[352.9 MiB]" memory.weights.total="240.1 MiB" memory.weights.repeating="195.4 MiB" memory.weights.nonrepeating="44.7 MiB" memory.graph.full="48.0 MiB" memory.graph.partial="48.0 MiB"
time=2025-03-12T10:13:06.200+05:30 level=DEBUG source=server.go:262 msg="compatible gpu libraries" compatible=[]
time=2025-03-12T10:13:06.205+05:30 level=DEBUG source=gpu.go:695 msg="no filter required for library cpu"
time=2025-03-12T10:13:06.206+05:30 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 --ctx-size 8192 --batch-size 512 --verbose --threads 4 --no-mmap --parallel 1 --port 40713"
time=2025-03-12T10:13:06.206+05:30 level=DEBUG source=server.go:398 msg=subprocess environment="[PATH=/opt/gradle/gradle-5.0/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/home/satya/Desktop/kafka/kafka_2.13-3.2.0/bin:/usr/local/go/bin LD_LIBRARY_PATH=/usr/local/lib/ollama]"
time=2025-03-12T10:13:06.210+05:30 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-03-12T10:13:06.210+05:30 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-03-12T10:13:06.214+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-03-12T10:13:06.321+05:30 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-03-12T10:13:06.322+05:30 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=4
time=2025-03-12T10:13:06.322+05:30 level=DEBUG source=ggml.go:89 msg="ggml backend load all from path" path=/usr/local/lib/ollama
time=2025-03-12T10:13:06.323+05:30 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:40713"
ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-haswell.so score: 0
ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-sandybridge.so score: 20
ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-sapphirerapids.so score: 0
ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-alderlake.so score: 0
ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-skylakex.so score: 0
ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-icelake.so score: 0
load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so
llama_model_loader: loaded meta data with 24 key-value pairs and 112 tensors from /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 (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 = nomic-bert
llama_model_loader: - kv 1: general.name str = nomic-embed-text-v1.5
llama_model_loader: - kv 2: nomic-bert.block_count u32 = 12
llama_model_loader: - kv 3: nomic-bert.context_length u32 = 2048
llama_model_loader: - kv 4: nomic-bert.embedding_length u32 = 768
llama_model_loader: - kv 5: nomic-bert.feed_forward_length u32 = 3072
llama_model_loader: - kv 6: nomic-bert.attention.head_count u32 = 12
llama_model_loader: - kv 7: nomic-bert.attention.layer_norm_epsilon f32 = 0.000000
llama_model_loader: - kv 8: general.file_type u32 = 1
llama_model_loader: - kv 9: nomic-bert.attention.causal bool = false
llama_model_loader: - kv 10: nomic-bert.pooling_type u32 = 1
llama_model_loader: - kv 11: nomic-bert.rope.freq_base f32 = 1000.000000
llama_model_loader: - kv 12: tokenizer.ggml.token_type_count u32 = 2
llama_model_loader: - kv 13: tokenizer.ggml.bos_token_id u32 = 101
llama_model_loader: - kv 14: tokenizer.ggml.eos_token_id u32 = 102
llama_model_loader: - kv 15: tokenizer.ggml.model str = bert
time=2025-03-12T10:13:06.469+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,30522] = ["[PAD]", "[unused0]", "[unused1]", "...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,30522] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,30522] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 100
llama_model_loader: - kv 20: tokenizer.ggml.seperator_token_id u32 = 102
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 22: tokenizer.ggml.cls_token_id u32 = 101
llama_model_loader: - kv 23: tokenizer.ggml.mask_token_id u32 = 103
llama_model_loader: - type f32: 51 tensors
llama_model_loader: - type f16: 61 tensors
llm_load_vocab: control token: 103 '[MASK]' is not marked as EOG
llm_load_vocab: control token: 0 '[PAD]' is not marked as EOG
llm_load_vocab: control token: 102 '[SEP]' is not marked as EOG
llm_load_vocab: control token: 101 '[CLS]' is not marked as EOG
llm_load_vocab: control token: 100 '[UNK]' is not marked as EOG
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 5
llm_load_vocab: token to piece cache size = 0.2032 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = nomic-bert
llm_load_print_meta: vocab type = WPM
llm_load_print_meta: n_vocab = 30522
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 2048
llm_load_print_meta: n_embd = 768
llm_load_print_meta: n_layer = 12
llm_load_print_meta: n_head = 12
llm_load_print_meta: n_head_kv = 12
llm_load_print_meta: n_rot = 64
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 64
llm_load_print_meta: n_embd_head_v = 64
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 768
llm_load_print_meta: n_embd_v_gqa = 768
llm_load_print_meta: f_norm_eps = 1.0e-12
llm_load_print_meta: f_norm_rms_eps = 0.0e+00
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 3072
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 0
llm_load_print_meta: pooling type = 1
llm_load_print_meta: rope type = 2
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 1000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 2048
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: ssm_dt_b_c_rms = 0
llm_load_print_meta: model type = 137M
llm_load_print_meta: model ftype = F16
llm_load_print_meta: model params = 136.73 M
llm_load_print_meta: model size = 260.86 MiB (16.00 BPW)
llm_load_print_meta: general.name = nomic-embed-text-v1.5
llm_load_print_meta: BOS token = 101 '[CLS]'
llm_load_print_meta: EOS token = 102 '[SEP]'
llm_load_print_meta: UNK token = 100 '[UNK]'
llm_load_print_meta: SEP token = 102 '[SEP]'
llm_load_print_meta: PAD token = 0 '[PAD]'
llm_load_print_meta: CLS token = 101 '[CLS]'
llm_load_print_meta: MASK token = 103 '[MASK]'
llm_load_print_meta: LF token = 0 '[PAD]'
llm_load_print_meta: EOG token = 102 '[SEP]'
llm_load_print_meta: max token length = 21
llm_load_tensors: CPU model buffer size = 260.86 MiB
load_all_data: no device found for buffer type CPU for async uploads
time=2025-03-12T10:13:21.143+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.17"
time=2025-03-12T10:13:22.826+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.18"
time=2025-03-12T10:13:23.367+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.19"
time=2025-03-12T10:13:25.260+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.21"
time=2025-03-12T10:13:26.544+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.22"
time=2025-03-12T10:13:28.172+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.24"
time=2025-03-12T10:13:29.197+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.26"
time=2025-03-12T10:13:30.207+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.28"
time=2025-03-12T10:13:31.723+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.29"
time=2025-03-12T10:13:33.898+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.31"
time=2025-03-12T10:13:34.680+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.33"
time=2025-03-12T10:13:36.195+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.34"
time=2025-03-12T10:13:38.503+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.36"
time=2025-03-12T10:13:39.264+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.38"
time=2025-03-12T10:13:40.022+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.40"
time=2025-03-12T10:13:41.282+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.41"
time=2025-03-12T10:13:43.000+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.43"
time=2025-03-12T10:13:44.834+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.45"
time=2025-03-12T10:13:45.091+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.46"
time=2025-03-12T10:13:45.355+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.46"
time=2025-03-12T10:13:46.866+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.48"
time=2025-03-12T10:13:47.984+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.50"
time=2025-03-12T10:13:50.294+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.52"
time=2025-03-12T10:13:50.546+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.53"
time=2025-03-12T10:13:51.303+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.55"
time=2025-03-12T10:13:52.323+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.57"
time=2025-03-12T10:13:53.426+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.59"
time=2025-03-12T10:13:54.393+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.60"
time=2025-03-12T10:13:55.477+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.62"
time=2025-03-12T10:13:56.511+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.64"
time=2025-03-12T10:13:57.019+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.65"
time=2025-03-12T10:13:58.039+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.67"
time=2025-03-12T10:13:58.293+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.67"
time=2025-03-12T10:13:59.315+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.69"
time=2025-03-12T10:14:00.113+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.71"
time=2025-03-12T10:14:01.397+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.72"
time=2025-03-12T10:14:02.080+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.74"
time=2025-03-12T10:14:02.342+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.74"
time=2025-03-12T10:14:03.105+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.76"
time=2025-03-12T10:14:04.127+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.78"
time=2025-03-12T10:14:05.000+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.79"
time=2025-03-12T10:14:05.508+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.81"
time=2025-03-12T10:14:05.830+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.81"
time=2025-03-12T10:14:07.138+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.83"
time=2025-03-12T10:14:10.006+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.84"
time=2025-03-12T10:14:11.335+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.86"
time=2025-03-12T10:14:12.354+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.87"
time=2025-03-12T10:14:12.607+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.88"
time=2025-03-12T10:14:14.600+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.90"
time=2025-03-12T10:14:16.579+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.91"
time=2025-03-12T10:14:17.433+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.93"
time=2025-03-12T10:14:18.251+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.94"
time=2025-03-12T10:14:18.756+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.95"
time=2025-03-12T10:14:19.021+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.97"
time=2025-03-12T10:14:19.800+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server not responding"
time=2025-03-12T10:14:20.090+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
time=2025-03-12T10:14:20.091+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.98"
llama_new_context_with_model: n_seq_max = 1
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_ctx_per_seq = 8192
llama_new_context_with_model: n_batch = 512
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 1000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: n_ctx_pre_seq (8192) > n_ctx_train (2048) -- possible training context overflow
llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 12, can_shift = 1
llama_kv_cache_init: layer 0: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 1: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 2: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 3: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 4: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 5: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 6: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 7: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 8: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 9: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 10: n_embd_k_gqa = 768, n_embd_v_gqa = 768
llama_kv_cache_init: layer 11: n_embd_k_gqa = 768, n_embd_v_gqa = 768
time=2025-03-12T10:14:21.098+05:30 level=DEBUG source=server.go:602 msg="model load progress 1.00"
time=2025-03-12T10:14:21.354+05:30 level=DEBUG source=server.go:605 msg="model load completed, waiting for server to become available" status="llm server loading model"
llama_kv_cache_init: CPU KV buffer size = 288.00 MiB
llama_new_context_with_model: KV self size = 288.00 MiB, K (f16): 144.00 MiB, V (f16): 144.00 MiB
llama_new_context_with_model: CPU output buffer size = 0.00 MiB
llama_new_context_with_model: CPU compute buffer size = 23.00 MiB
llama_new_context_with_model: graph nodes = 453
llama_new_context_with_model: graph splits = 1
time=2025-03-12T10:15:07.541+05:30 level=INFO source=server.go:596 msg="llama runner started in 121.32 seconds"
time=2025-03-12T10:15:07.616+05:30 level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6
time=2025-03-12T10:15:07.974+05:30 level=DEBUG source=server.go:968 msg="new runner detected, loading model for cgo tokenization"
llama_model_loader: loaded meta data with 24 key-value pairs and 112 tensors from /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 (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 = nomic-bert
llama_model_loader: - kv 1: general.name str = nomic-embed-text-v1.5
llama_model_loader: - kv 2: nomic-bert.block_count u32 = 12
llama_model_loader: - kv 3: nomic-bert.context_length u32 = 2048
llama_model_loader: - kv 4: nomic-bert.embedding_length u32 = 768
llama_model_loader: - kv 5: nomic-bert.feed_forward_length u32 = 3072
llama_model_loader: - kv 6: nomic-bert.attention.head_count u32 = 12
llama_model_loader: - kv 7: nomic-bert.attention.layer_norm_epsilon f32 = 0.000000
llama_model_loader: - kv 8: general.file_type u32 = 1
llama_model_loader: - kv 9: nomic-bert.attention.causal bool = false
llama_model_loader: - kv 10: nomic-bert.pooling_type u32 = 1
llama_model_loader: - kv 11: nomic-bert.rope.freq_base f32 = 1000.000000
llama_model_loader: - kv 12: tokenizer.ggml.token_type_count u32 = 2
llama_model_loader: - kv 13: tokenizer.ggml.bos_token_id u32 = 101
llama_model_loader: - kv 14: tokenizer.ggml.eos_token_id u32 = 102
llama_model_loader: - kv 15: tokenizer.ggml.model str = bert
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,30522] = ["[PAD]", "[unused0]", "[unused1]", "...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,30522] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,30522] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 100
llama_model_loader: - kv 20: tokenizer.ggml.seperator_token_id u32 = 102
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 22: tokenizer.ggml.cls_token_id u32 = 101
llama_model_loader: - kv 23: tokenizer.ggml.mask_token_id u32 = 103
llama_model_loader: - type f32: 51 tensors
llama_model_loader: - type f16: 61 tensors
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 5
llm_load_vocab: token to piece cache size = 0.2032 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = nomic-bert
llm_load_print_meta: vocab type = WPM
llm_load_print_meta: n_vocab = 30522
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 1
llm_load_print_meta: model type = ?B
llm_load_print_meta: model ftype = all F32
llm_load_print_meta: model params = 136.73 M
llm_load_print_meta: model size = 260.86 MiB (16.00 BPW)
llm_load_print_meta: general.name = nomic-embed-text-v1.5
llm_load_print_meta: BOS token = 101 '[CLS]'
llm_load_print_meta: EOS token = 102 '[SEP]'
llm_load_print_meta: UNK token = 100 '[UNK]'
llm_load_print_meta: SEP token = 102 '[SEP]'
llm_load_print_meta: PAD token = 0 '[PAD]'
llm_load_print_meta: CLS token = 101 '[CLS]'
llm_load_print_meta: MASK token = 103 '[MASK]'
llm_load_print_meta: LF token = 0 '[PAD]'
llm_load_print_meta: EOG token = 102 '[SEP]'
llm_load_print_meta: max token length = 21
llama_model_load: vocab only - skipping tensors
time=2025-03-12T10:15:10.166+05:30 level=DEBUG source=runner.go:741 msg="embedding request" content="{"TASKNAME": "Task1", "STATUS": "FAILED", "SPACE": "spac1", "STARTED TIMESTAMP": "2025-02-20T08:38:12.046Z", "FAILED ISSUE": "No Issue Mentioned", "FAILED DETAILS": "No Details Found", "RESOLUTION STEP": " 'steps'", "TASK COMPLETION DURATION": "5738.378999948502"}"
time=2025-03-12T10:15:10.589+05:30 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=112 used=0 remaining=112
time=2025-03-12T10:15:36.274+05:30 level=INFO source=server.go:915 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
time=2025-03-12T10:15:36.305+05:30 level=ERROR source=routes.go:477 msg="embedding generation failed" error="failed to encode response: json: unsupported value: NaN\n"
[GIN] 2025/03/12 - 10:15:36 | 500 | 2m30s | 127.0.0.1 | POST "/api/embed"
time=2025-03-12T10:15:36.372+05:30 level=DEBUG source=sched.go:466 msg="context for request finished"
time=2025-03-12T10:15:36.381+05:30 level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 duration=5m0s
time=2025-03-12T10:15:36.383+05:30 level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 refCount=0

<!-- gh-comment-id:2716568250 --> @satya-devloper commented on GitHub (Mar 12, 2025): time=2025-03-12T10:13:06.067+05:30 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="14.7 GiB" before.free="4.5 GiB" before.free_swap="2.0 GiB" now.total="14.7 GiB" now.free="4.5 GiB" now.free_swap="2.0 GiB" time=2025-03-12T10:13:06.067+05:30 level=DEBUG source=sched.go:181 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=0x55cc821a7b40 gpu_count=1 time=2025-03-12T10:13:06.167+05:30 level=DEBUG source=sched.go:211 msg="cpu mode with first model, loading" time=2025-03-12T10:13:06.188+05:30 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="14.7 GiB" before.free="4.5 GiB" before.free_swap="2.0 GiB" now.total="14.7 GiB" now.free="4.5 GiB" now.free_swap="2.0 GiB" time=2025-03-12T10:13:06.188+05:30 level=INFO source=server.go:100 msg="system memory" total="14.7 GiB" free="4.5 GiB" free_swap="2.0 GiB" time=2025-03-12T10:13:06.198+05:30 level=DEBUG source=memory.go:107 msg=evaluating library=cpu gpu_count=1 available="[4.5 GiB]" time=2025-03-12T10:13:06.199+05:30 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=13 layers.offload=0 layers.split="" memory.available="[4.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="352.9 MiB" memory.required.partial="0 B" memory.required.kv="24.0 MiB" memory.required.allocations="[352.9 MiB]" memory.weights.total="240.1 MiB" memory.weights.repeating="195.4 MiB" memory.weights.nonrepeating="44.7 MiB" memory.graph.full="48.0 MiB" memory.graph.partial="48.0 MiB" time=2025-03-12T10:13:06.200+05:30 level=DEBUG source=server.go:262 msg="compatible gpu libraries" compatible=[] time=2025-03-12T10:13:06.205+05:30 level=DEBUG source=gpu.go:695 msg="no filter required for library cpu" time=2025-03-12T10:13:06.206+05:30 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 --ctx-size 8192 --batch-size 512 --verbose --threads 4 --no-mmap --parallel 1 --port 40713" time=2025-03-12T10:13:06.206+05:30 level=DEBUG source=server.go:398 msg=subprocess environment="[PATH=/opt/gradle/gradle-5.0/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/home/satya/Desktop/kafka/kafka_2.13-3.2.0/bin:/usr/local/go/bin LD_LIBRARY_PATH=/usr/local/lib/ollama]" time=2025-03-12T10:13:06.210+05:30 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-03-12T10:13:06.210+05:30 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-03-12T10:13:06.214+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-03-12T10:13:06.321+05:30 level=INFO source=runner.go:936 msg="starting go runner" time=2025-03-12T10:13:06.322+05:30 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=4 time=2025-03-12T10:13:06.322+05:30 level=DEBUG source=ggml.go:89 msg="ggml backend load all from path" path=/usr/local/lib/ollama time=2025-03-12T10:13:06.323+05:30 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:40713" ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-haswell.so score: 0 ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-sandybridge.so score: 20 ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-sapphirerapids.so score: 0 ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-alderlake.so score: 0 ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-skylakex.so score: 0 ggml_backend_load_best: /usr/local/lib/ollama/libggml-cpu-icelake.so score: 0 load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-sandybridge.so llama_model_loader: loaded meta data with 24 key-value pairs and 112 tensors from /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 (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 = nomic-bert llama_model_loader: - kv 1: general.name str = nomic-embed-text-v1.5 llama_model_loader: - kv 2: nomic-bert.block_count u32 = 12 llama_model_loader: - kv 3: nomic-bert.context_length u32 = 2048 llama_model_loader: - kv 4: nomic-bert.embedding_length u32 = 768 llama_model_loader: - kv 5: nomic-bert.feed_forward_length u32 = 3072 llama_model_loader: - kv 6: nomic-bert.attention.head_count u32 = 12 llama_model_loader: - kv 7: nomic-bert.attention.layer_norm_epsilon f32 = 0.000000 llama_model_loader: - kv 8: general.file_type u32 = 1 llama_model_loader: - kv 9: nomic-bert.attention.causal bool = false llama_model_loader: - kv 10: nomic-bert.pooling_type u32 = 1 llama_model_loader: - kv 11: nomic-bert.rope.freq_base f32 = 1000.000000 llama_model_loader: - kv 12: tokenizer.ggml.token_type_count u32 = 2 llama_model_loader: - kv 13: tokenizer.ggml.bos_token_id u32 = 101 llama_model_loader: - kv 14: tokenizer.ggml.eos_token_id u32 = 102 llama_model_loader: - kv 15: tokenizer.ggml.model str = bert time=2025-03-12T10:13:06.469+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,30522] = ["[PAD]", "[unused0]", "[unused1]", "... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,30522] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,30522] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 100 llama_model_loader: - kv 20: tokenizer.ggml.seperator_token_id u32 = 102 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 22: tokenizer.ggml.cls_token_id u32 = 101 llama_model_loader: - kv 23: tokenizer.ggml.mask_token_id u32 = 103 llama_model_loader: - type f32: 51 tensors llama_model_loader: - type f16: 61 tensors llm_load_vocab: control token: 103 '[MASK]' is not marked as EOG llm_load_vocab: control token: 0 '[PAD]' is not marked as EOG llm_load_vocab: control token: 102 '[SEP]' is not marked as EOG llm_load_vocab: control token: 101 '[CLS]' is not marked as EOG llm_load_vocab: control token: 100 '[UNK]' is not marked as EOG llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 5 llm_load_vocab: token to piece cache size = 0.2032 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = nomic-bert llm_load_print_meta: vocab type = WPM llm_load_print_meta: n_vocab = 30522 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 2048 llm_load_print_meta: n_embd = 768 llm_load_print_meta: n_layer = 12 llm_load_print_meta: n_head = 12 llm_load_print_meta: n_head_kv = 12 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 64 llm_load_print_meta: n_embd_head_v = 64 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 768 llm_load_print_meta: n_embd_v_gqa = 768 llm_load_print_meta: f_norm_eps = 1.0e-12 llm_load_print_meta: f_norm_rms_eps = 0.0e+00 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 3072 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 0 llm_load_print_meta: pooling type = 1 llm_load_print_meta: rope type = 2 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 2048 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 137M llm_load_print_meta: model ftype = F16 llm_load_print_meta: model params = 136.73 M llm_load_print_meta: model size = 260.86 MiB (16.00 BPW) llm_load_print_meta: general.name = nomic-embed-text-v1.5 llm_load_print_meta: BOS token = 101 '[CLS]' llm_load_print_meta: EOS token = 102 '[SEP]' llm_load_print_meta: UNK token = 100 '[UNK]' llm_load_print_meta: SEP token = 102 '[SEP]' llm_load_print_meta: PAD token = 0 '[PAD]' llm_load_print_meta: CLS token = 101 '[CLS]' llm_load_print_meta: MASK token = 103 '[MASK]' llm_load_print_meta: LF token = 0 '[PAD]' llm_load_print_meta: EOG token = 102 '[SEP]' llm_load_print_meta: max token length = 21 llm_load_tensors: CPU model buffer size = 260.86 MiB load_all_data: no device found for buffer type CPU for async uploads time=2025-03-12T10:13:21.143+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.17" time=2025-03-12T10:13:22.826+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.18" time=2025-03-12T10:13:23.367+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.19" time=2025-03-12T10:13:25.260+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.21" time=2025-03-12T10:13:26.544+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.22" time=2025-03-12T10:13:28.172+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.24" time=2025-03-12T10:13:29.197+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.26" time=2025-03-12T10:13:30.207+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.28" time=2025-03-12T10:13:31.723+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.29" time=2025-03-12T10:13:33.898+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.31" time=2025-03-12T10:13:34.680+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.33" time=2025-03-12T10:13:36.195+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.34" time=2025-03-12T10:13:38.503+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.36" time=2025-03-12T10:13:39.264+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.38" time=2025-03-12T10:13:40.022+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.40" time=2025-03-12T10:13:41.282+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.41" time=2025-03-12T10:13:43.000+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.43" time=2025-03-12T10:13:44.834+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.45" time=2025-03-12T10:13:45.091+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.46" time=2025-03-12T10:13:45.355+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.46" time=2025-03-12T10:13:46.866+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.48" time=2025-03-12T10:13:47.984+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.50" time=2025-03-12T10:13:50.294+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.52" time=2025-03-12T10:13:50.546+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.53" time=2025-03-12T10:13:51.303+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.55" time=2025-03-12T10:13:52.323+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.57" time=2025-03-12T10:13:53.426+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.59" time=2025-03-12T10:13:54.393+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.60" time=2025-03-12T10:13:55.477+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.62" time=2025-03-12T10:13:56.511+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.64" time=2025-03-12T10:13:57.019+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.65" time=2025-03-12T10:13:58.039+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.67" time=2025-03-12T10:13:58.293+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.67" time=2025-03-12T10:13:59.315+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.69" time=2025-03-12T10:14:00.113+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.71" time=2025-03-12T10:14:01.397+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.72" time=2025-03-12T10:14:02.080+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.74" time=2025-03-12T10:14:02.342+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.74" time=2025-03-12T10:14:03.105+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.76" time=2025-03-12T10:14:04.127+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.78" time=2025-03-12T10:14:05.000+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.79" time=2025-03-12T10:14:05.508+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.81" time=2025-03-12T10:14:05.830+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.81" time=2025-03-12T10:14:07.138+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.83" time=2025-03-12T10:14:10.006+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.84" time=2025-03-12T10:14:11.335+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.86" time=2025-03-12T10:14:12.354+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.87" time=2025-03-12T10:14:12.607+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.88" time=2025-03-12T10:14:14.600+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.90" time=2025-03-12T10:14:16.579+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.91" time=2025-03-12T10:14:17.433+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.93" time=2025-03-12T10:14:18.251+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.94" time=2025-03-12T10:14:18.756+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.95" time=2025-03-12T10:14:19.021+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.97" time=2025-03-12T10:14:19.800+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server not responding" time=2025-03-12T10:14:20.090+05:30 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" time=2025-03-12T10:14:20.091+05:30 level=DEBUG source=server.go:602 msg="model load progress 0.98" llama_new_context_with_model: n_seq_max = 1 llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_ctx_per_seq = 8192 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 1000.0 llama_new_context_with_model: freq_scale = 1 llama_new_context_with_model: n_ctx_pre_seq (8192) > n_ctx_train (2048) -- possible training context overflow llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 12, can_shift = 1 llama_kv_cache_init: layer 0: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 1: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 2: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 3: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 4: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 5: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 6: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 7: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 8: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 9: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 10: n_embd_k_gqa = 768, n_embd_v_gqa = 768 llama_kv_cache_init: layer 11: n_embd_k_gqa = 768, n_embd_v_gqa = 768 time=2025-03-12T10:14:21.098+05:30 level=DEBUG source=server.go:602 msg="model load progress 1.00" time=2025-03-12T10:14:21.354+05:30 level=DEBUG source=server.go:605 msg="model load completed, waiting for server to become available" status="llm server loading model" llama_kv_cache_init: CPU KV buffer size = 288.00 MiB llama_new_context_with_model: KV self size = 288.00 MiB, K (f16): 144.00 MiB, V (f16): 144.00 MiB llama_new_context_with_model: CPU output buffer size = 0.00 MiB llama_new_context_with_model: CPU compute buffer size = 23.00 MiB llama_new_context_with_model: graph nodes = 453 llama_new_context_with_model: graph splits = 1 time=2025-03-12T10:15:07.541+05:30 level=INFO source=server.go:596 msg="llama runner started in 121.32 seconds" time=2025-03-12T10:15:07.616+05:30 level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 time=2025-03-12T10:15:07.974+05:30 level=DEBUG source=server.go:968 msg="new runner detected, loading model for cgo tokenization" llama_model_loader: loaded meta data with 24 key-value pairs and 112 tensors from /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 (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 = nomic-bert llama_model_loader: - kv 1: general.name str = nomic-embed-text-v1.5 llama_model_loader: - kv 2: nomic-bert.block_count u32 = 12 llama_model_loader: - kv 3: nomic-bert.context_length u32 = 2048 llama_model_loader: - kv 4: nomic-bert.embedding_length u32 = 768 llama_model_loader: - kv 5: nomic-bert.feed_forward_length u32 = 3072 llama_model_loader: - kv 6: nomic-bert.attention.head_count u32 = 12 llama_model_loader: - kv 7: nomic-bert.attention.layer_norm_epsilon f32 = 0.000000 llama_model_loader: - kv 8: general.file_type u32 = 1 llama_model_loader: - kv 9: nomic-bert.attention.causal bool = false llama_model_loader: - kv 10: nomic-bert.pooling_type u32 = 1 llama_model_loader: - kv 11: nomic-bert.rope.freq_base f32 = 1000.000000 llama_model_loader: - kv 12: tokenizer.ggml.token_type_count u32 = 2 llama_model_loader: - kv 13: tokenizer.ggml.bos_token_id u32 = 101 llama_model_loader: - kv 14: tokenizer.ggml.eos_token_id u32 = 102 llama_model_loader: - kv 15: tokenizer.ggml.model str = bert llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,30522] = ["[PAD]", "[unused0]", "[unused1]", "... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,30522] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,30522] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 100 llama_model_loader: - kv 20: tokenizer.ggml.seperator_token_id u32 = 102 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 22: tokenizer.ggml.cls_token_id u32 = 101 llama_model_loader: - kv 23: tokenizer.ggml.mask_token_id u32 = 103 llama_model_loader: - type f32: 51 tensors llama_model_loader: - type f16: 61 tensors llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 5 llm_load_vocab: token to piece cache size = 0.2032 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = nomic-bert llm_load_print_meta: vocab type = WPM llm_load_print_meta: n_vocab = 30522 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 1 llm_load_print_meta: model type = ?B llm_load_print_meta: model ftype = all F32 llm_load_print_meta: model params = 136.73 M llm_load_print_meta: model size = 260.86 MiB (16.00 BPW) llm_load_print_meta: general.name = nomic-embed-text-v1.5 llm_load_print_meta: BOS token = 101 '[CLS]' llm_load_print_meta: EOS token = 102 '[SEP]' llm_load_print_meta: UNK token = 100 '[UNK]' llm_load_print_meta: SEP token = 102 '[SEP]' llm_load_print_meta: PAD token = 0 '[PAD]' llm_load_print_meta: CLS token = 101 '[CLS]' llm_load_print_meta: MASK token = 103 '[MASK]' llm_load_print_meta: LF token = 0 '[PAD]' llm_load_print_meta: EOG token = 102 '[SEP]' llm_load_print_meta: max token length = 21 llama_model_load: vocab only - skipping tensors time=2025-03-12T10:15:10.166+05:30 level=DEBUG source=runner.go:741 msg="embedding request" content="{\"TASKNAME\": \"Task1\", \"STATUS\": \"FAILED\", \"SPACE\": \"spac1\", \"STARTED TIMESTAMP\": \"2025-02-20T08:38:12.046Z\", \"FAILED ISSUE\": \"No Issue Mentioned\", \"FAILED DETAILS\": \"No Details Found\", \"RESOLUTION STEP\": \" 'steps'\", \"TASK COMPLETION DURATION\": \"5738.378999948502\"}" time=2025-03-12T10:15:10.589+05:30 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=112 used=0 remaining=112 time=2025-03-12T10:15:36.274+05:30 level=INFO source=server.go:915 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" time=2025-03-12T10:15:36.305+05:30 level=ERROR source=routes.go:477 msg="embedding generation failed" error="failed to encode response: json: unsupported value: NaN\n" [GIN] 2025/03/12 - 10:15:36 | 500 | 2m30s | 127.0.0.1 | POST "/api/embed" time=2025-03-12T10:15:36.372+05:30 level=DEBUG source=sched.go:466 msg="context for request finished" time=2025-03-12T10:15:36.381+05:30 level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 duration=5m0s time=2025-03-12T10:15:36.383+05:30 level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 refCount=0

GiteaMirror commented 2026-04-22 12:55:44 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 12, 2025):

@mxyng @rick-github This is the log with debug enabled, I m getting response NaN error

<!-- gh-comment-id:2716569903 --> @satya-devloper commented on GitHub (Mar 12, 2025): @mxyng @rick-github This is the log with debug enabled, I m getting response NaN error

GiteaMirror commented 2026-04-22 12:55:45 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 12, 2025):

@rick-github @mxyng , One more thing my ollama is running behind proxy

<!-- gh-comment-id:2716954493 --> @satya-devloper commented on GitHub (Mar 12, 2025): @rick-github @mxyng , One more thing my ollama is running behind proxy

GiteaMirror commented 2026-04-22 12:55:45 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Mar 12, 2025):

This looks pretty normal, except for the model taking two minutes to load. Is the machine virtual or some sort of containerized system, eg proxmox?

<!-- gh-comment-id:2718138782 --> @rick-github commented on GitHub (Mar 12, 2025): This looks pretty normal, except for the model taking two minutes to load. Is the machine virtual or some sort of containerized system, eg proxmox?

GiteaMirror commented 2026-04-22 12:55:46 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 13, 2025):

@rick-github its just a linux box hosted in our data center

<!-- gh-comment-id:2720038085 --> @satya-devloper commented on GitHub (Mar 13, 2025): @rick-github its just a linux box hosted in our data center

GiteaMirror commented 2026-04-22 12:55:46 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 17, 2025):

@rick-github any update

<!-- gh-comment-id:2728120075 --> @satya-devloper commented on GitHub (Mar 17, 2025): @rick-github any update

GiteaMirror commented 2026-04-22 12:55:46 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Mar 17, 2025):

I am unable to replicate the problem, so need more information.

What's the output of sha256sum home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 ?

Stop the server, restart it, run a test, and post the full log, including the start that shows configuration information and device detection.

<!-- gh-comment-id:2729279845 --> @rick-github commented on GitHub (Mar 17, 2025): I am unable to replicate the problem, so need more information. What's the output of `sha256sum home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6` ? Stop the server, restart it, run a test, and post the full log, including the start that shows configuration information and device detection.

GiteaMirror commented 2026-04-22 12:55:47 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 20, 2025):

@rick-github output is : 98e675c8c9e9cd1c71cab9dfca37c83406eba35a4692df55b0fa692f78b29638 sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6

<!-- gh-comment-id:2739032423 --> @satya-devloper commented on GitHub (Mar 20, 2025): @rick-github output is : 98e675c8c9e9cd1c71cab9dfca37c83406eba35a4692df55b0fa692f78b29638 sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6

GiteaMirror commented 2026-04-22 12:55:47 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Mar 20, 2025):

Your model is damaged, it has the wrong sha256 hash. Delete it (ollama rm nomic-embed-text) and re-download it (ollama pull nomic-embed-text).

<!-- gh-comment-id:2739804174 --> @rick-github commented on GitHub (Mar 20, 2025): Your model is damaged, it has the wrong sha256 hash. Delete it (`ollama rm nomic-embed-text`) and re-download it (`ollama pull nomic-embed-text`).

GiteaMirror commented 2026-04-22 12:55:48 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Mar 25, 2025):

same issue after that also @rick-github

<!-- gh-comment-id:2751898708 --> @satya-devloper commented on GitHub (Mar 25, 2025): same issue after that also @rick-github

GiteaMirror commented 2026-04-22 12:55:48 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Mar 25, 2025):

Do the sha256 signatures match?

<!-- gh-comment-id:2751902995 --> @rick-github commented on GitHub (Mar 25, 2025): Do the sha256 signatures match?

GiteaMirror commented 2026-04-22 12:55:49 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Mar 25, 2025):

What;s the output of

ls -l /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6

<!-- gh-comment-id:2751913655 --> @rick-github commented on GitHub (Mar 25, 2025): What;s the output of ``` ls -l /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 ```

GiteaMirror commented 2026-04-22 12:55:49 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Apr 3, 2025):

output is:
-rw-r--r-- 1 satya satya 274290656 Mar 8 01:40 /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6

<!-- gh-comment-id:2775563422 --> @satya-devloper commented on GitHub (Apr 3, 2025): output is: -rw-r--r-- 1 satya satya 274290656 Mar 8 01:40 /home/satya/.ollama/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6

GiteaMirror commented 2026-04-22 12:55:50 -05:00

Author

Owner

Copy Link

@rick-github commented on GitHub (Apr 3, 2025):

Do the sha256 signatures match?

<!-- gh-comment-id:2775585283 --> @rick-github commented on GitHub (Apr 3, 2025): Do the sha256 signatures match?

GiteaMirror commented 2026-04-22 12:55:50 -05:00

Author

Owner

Copy Link

@satya-devloper commented on GitHub (Apr 4, 2025):

yes matching

<!-- gh-comment-id:2777628823 --> @satya-devloper commented on GitHub (Apr 4, 2025): yes matching

GiteaMirror commented 2026-04-22 12:55:51 -05:00

Author

Owner

Copy Link

@NikolasTh90 commented on GitHub (Jun 23, 2025):

I have the same problem

<!-- gh-comment-id:2996258504 --> @NikolasTh90 commented on GitHub (Jun 23, 2025): I have the same problem

GiteaMirror commented 2026-04-22 12:55:51 -05:00

Author

Owner

Copy Link

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

Have you checked the SHA256 and tried re-downloading the model?

<!-- gh-comment-id:2996295755 --> @rick-github commented on GitHub (Jun 23, 2025): Have you checked the SHA256 and tried re-downloading the model?

GiteaMirror commented 2026-04-22 12:55:52 -05:00

Author

Owner

Copy Link

@NikolasTh90 commented on GitHub (Jun 23, 2025):

I am on ollama 0.9.2 CU124 bare metal on RTX 4090.

<!-- gh-comment-id:2996312161 --> @NikolasTh90 commented on GitHub (Jun 23, 2025): I am on ollama 0.9.2 CU124 bare metal on RTX 4090.

GiteaMirror commented 2026-04-22 12:55:52 -05:00

Author

Owner

Copy Link

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

Have you checked the SHA256 and tried re-downloading the model?

<!-- gh-comment-id:2996316288 --> @rick-github commented on GitHub (Jun 23, 2025): Have you checked the SHA256 and tried re-downloading the model?

GiteaMirror commented 2026-04-22 12:55:53 -05:00

Author

Owner

Copy Link

@NikolasTh90 commented on GitHub (Jun 23, 2025):

Yes I have checked sha and redownloaded anyway. I am using dengcao/Qwen3-Embedding-8B:F16

<!-- gh-comment-id:2996320380 --> @NikolasTh90 commented on GitHub (Jun 23, 2025): Yes I have checked sha and redownloaded anyway. I am using dengcao/Qwen3-Embedding-8B:F16

GiteaMirror commented 2026-04-22 12:55:54 -05:00

Author

Owner

Copy Link

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

What was the output of the sha sum?

<!-- gh-comment-id:2996323459 --> @rick-github commented on GitHub (Jun 23, 2025): What was the output of the sha sum?

GiteaMirror commented 2026-04-22 12:55:54 -05:00

Author

Owner

Copy Link

@NikolasTh90 commented on GitHub (Jun 23, 2025):

.ollama/models/blobs$ sha256sum sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055

OUT:
01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055

<!-- gh-comment-id:2996370930 --> @NikolasTh90 commented on GitHub (Jun 23, 2025): .ollama/models/blobs$ sha256sum sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 OUT: 01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055

GiteaMirror commented 2026-04-22 12:55:55 -05:00

Author

Owner

Copy Link

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

Server logs with OLLAMA_DEBUG=2 will aid in debugging.

<!-- gh-comment-id:2996378678 --> @rick-github commented on GitHub (Jun 23, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) with `OLLAMA_DEBUG=2` will aid in debugging.

GiteaMirror commented 2026-04-22 12:55:56 -05:00

Author

Owner

Copy Link

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

The model works with a simple test:

$ ollama -v
ollama version is 0.9.2
$ for i in {1..5} ; do curl -s http://localhost:11434/api/embed -d '{"model":"dengcao/Qwen3-Embedding-8B:F16","input":"Llamas are members of the camelid family"}' | jq -c '.embeddings[]|.[0:3] + ["..."] + .[-3:]' ; done
[0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934]
[0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934]
[0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934]
[0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934]
[0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934]

<!-- gh-comment-id:2996390621 --> @rick-github commented on GitHub (Jun 23, 2025): The model works with a simple test: ``` $ ollama -v ollama version is 0.9.2 $ for i in {1..5} ; do curl -s http://localhost:11434/api/embed -d '{"model":"dengcao/Qwen3-Embedding-8B:F16","input":"Llamas are members of the camelid family"}' | jq -c '.embeddings[]|.[0:3] + ["..."] + .[-3:]' ; done [0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934] [0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934] [0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934] [0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934] [0.00937686,-0.008833623,-0.0025234958,"...",0.013162558,-0.0036315455,0.012727934] ```

GiteaMirror commented 2026-04-22 12:55:56 -05:00

Author

Owner

Copy Link

@NikolasTh90 commented on GitHub (Jun 23, 2025):

$ for i in {1..5} ; do curl -s http://localhost:11434/api/embed -d '{"model":"dengcao/Qwen3-Embedding-8B:F16","input":"Llamas are members of the camelid family"}' | jq -c '.embeddings[]|.[0:3] + ["..."] + .[-3:]' ; done
[0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551]
[0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551]
[0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551]
[0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551]
[0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551]
$ ollama -v
ollama version is 0.9.2

Seems like ollama is not the problem.

I am using continue.dev, probably there is a problem with the payload sent to be embedded.

<!-- gh-comment-id:2996409862 --> @NikolasTh90 commented on GitHub (Jun 23, 2025): $ for i in {1..5} ; do curl -s http://localhost:11434/api/embed -d '{"model":"dengcao/Qwen3-Embedding-8B:F16","input":"Llamas are members of the camelid family"}' | jq -c '.embeddings[]|.[0:3] + ["..."] + .[-3:]' ; done [0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551] [0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551] [0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551] [0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551] [0.009309137,-0.008815658,-0.0025224872,"...",0.0128948875,-0.0035430363,0.01299551] $ ollama -v ollama version is 0.9.2 Seems like ollama is not the problem. I am using continue.dev, probably there is a problem with the payload sent to be embedded.

GiteaMirror commented 2026-04-22 12:55:57 -05:00

Author

Owner

Copy Link

@NikolasTh90 commented on GitHub (Jun 23, 2025):

I am leaving my debug trace
`Ιουν 23 16:12:49 brainiac ollama[116520]: CUDA driver version: 12.4
Ιουν 23 16:12:49 brainiac ollama[116520]: calling cuDeviceGetCount
Ιουν 23 16:12:49 brainiac ollama[116520]: device count 1
Ιουν 23 16:12:49 brainiac ollama[116520]: time=2025-06-23T16:12:49.946+03:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=/usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01
Ιουν 23 16:12:50 brainiac ollama[116520]: [GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01] CUDA totalMem 23995mb
Ιουν 23 16:12:50 brainiac ollama[116520]: [GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01] CUDA freeMem 20180mb
Ιουν 23 16:12:50 brainiac ollama[116520]: [GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01] Compute Capability 8.9
Ιουν 23 16:12:50 brainiac ollama[116520]: time=2025-06-23T16:12:50.194+03:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu"
Ιουν 23 16:12:50 brainiac ollama[116520]: releasing cuda driver library
Ιουν 23 16:12:50 brainiac ollama[116520]: time=2025-06-23T16:12:50.194+03:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="23.4 GiB" available="19.7 GiB"
Ιουν 23 16:12:56 brainiac ollama[116520]: time=2025-06-23T16:12:56.932+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32
Ιουν 23 16:12:56 brainiac ollama[116520]: time=2025-06-23T16:12:56.932+03:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="188.5 GiB" before.free="181.1 GiB" before.free_swap="2.0 GiB" now.total="188.5 GiB" now.free="181.0 GiB" now.free_swap="2.0 GiB"
Ιουν 23 16:12:56 brainiac ollama[116520]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuInit - 0x7cff1267ce20
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDriverGetVersion - 0x7cff1267ce40
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetCount - 0x7cff1267ce80
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGet - 0x7cff1267ce60
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetAttribute - 0x7cff1267cf60
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetUuid - 0x7cff1267cec0
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetName - 0x7cff1267cea0
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuCtxCreate_v3 - 0x7cff1267d140
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuMemGetInfo_v2 - 0x7cff12687080
Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuCtxDestroy - 0x7cff126e19c0
Ιουν 23 16:12:56 brainiac ollama[116520]: calling cuInit
Ιουν 23 16:12:56 brainiac ollama[116520]: calling cuDriverGetVersion
Ιουν 23 16:12:56 brainiac ollama[116520]: raw version 0x2f08
Ιουν 23 16:12:56 brainiac ollama[116520]: CUDA driver version: 12.4
Ιουν 23 16:12:56 brainiac ollama[116520]: calling cuDeviceGetCount
Ιουν 23 16:12:56 brainiac ollama[116520]: device count 1
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.070+03:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="23.4 GiB" before.free="19.7 GiB" now.total="23.4 GiB" now.free="19.7 GiB" now.used="3.7 GiB"
Ιουν 23 16:12:57 brainiac ollama[116520]: releasing cuda driver library
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.070+03:00 level=DEBUG source=sched.go:185 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.077+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.084+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.084+03:00 level=DEBUG source=sched.go:228 msg="loading first model" model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.084+03:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[19.7 GiB]"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.085+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=qwen3.vision.block_count default=0
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.085+03:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 gpu=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 parallel=2 available=21160460288 required="16.8 GiB"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.085+03:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="188.5 GiB" before.free="181.0 GiB" before.free_swap="2.0 GiB" now.total="188.5 GiB" now.free="181.0 GiB" now.free_swap="2.0 GiB"
Ιουν 23 16:12:57 brainiac ollama[116520]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuInit - 0x7cff1267ce20
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDriverGetVersion - 0x7cff1267ce40
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetCount - 0x7cff1267ce80
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGet - 0x7cff1267ce60
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetAttribute - 0x7cff1267cf60
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetUuid - 0x7cff1267cec0
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetName - 0x7cff1267cea0
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuCtxCreate_v3 - 0x7cff1267d140
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuMemGetInfo_v2 - 0x7cff12687080
Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuCtxDestroy - 0x7cff126e19c0
Ιουν 23 16:12:57 brainiac ollama[116520]: calling cuInit
Ιουν 23 16:12:57 brainiac ollama[116520]: calling cuDriverGetVersion
Ιουν 23 16:12:57 brainiac ollama[116520]: raw version 0x2f08
Ιουν 23 16:12:57 brainiac ollama[116520]: CUDA driver version: 12.4
Ιουν 23 16:12:57 brainiac ollama[116520]: calling cuDeviceGetCount
Ιουν 23 16:12:57 brainiac ollama[116520]: device count 1
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="23.4 GiB" before.free="19.7 GiB" now.total="23.4 GiB" now.free="19.7 GiB" now.used="3.7 GiB"
Ιουν 23 16:12:57 brainiac ollama[116520]: releasing cuda driver library
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=INFO source=server.go:135 msg="system memory" total="188.5 GiB" free="181.0 GiB" free_swap="2.0 GiB"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[19.7 GiB]"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=qwen3.vision.block_count default=0
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=INFO source=server.go:168 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=37 layers.split="" memory.available="[19.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="16.8 GiB" memory.required.partial="16.8 GiB" memory.required.kv="1.1 GiB" memory.required.allocations="[16.8 GiB]" memory.weights.total="14.1 GiB" memory.weights.repeating="12.9 GiB" memory.weights.nonrepeating="1.2 GiB" memory.graph.full="768.0 MiB" memory.graph.partial="768.0 MiB"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=server.go:284 msg="compatible gpu libraries" compatible="[cuda_v12 cuda_v11]"
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: loaded meta data with 27 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 (version GGUF V3 (latest))
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 0: general.architecture str = qwen3
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 1: general.type str = model
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B Bf16
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 4: general.size_label str = 8B
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 5: qwen3.block_count u32 = 36
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 6: qwen3.context_length u32 = 40960
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 7: qwen3.embedding_length u32 = 4096
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 12288
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 32
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 15: general.file_type u32 = 1
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 16: general.quantization_version u32 = 2
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 18: tokenizer.ggml.pre str = qwen2
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,151665] = ["!", """, "#", "$", "%", "&", "'", ...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 151645
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 151643
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = false
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 26: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f32: 145 tensors
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f16: 253 tensors
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file format = GGUF V3 (latest)
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file type = F16
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file size = 14.10 GiB (16.00 BPW)
Ιουν 23 16:12:57 brainiac ollama[116520]: init_tokenizer: initializing tokenizer for type 2
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151660 '<|fim_middle|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151659 '<|fim_prefix|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151653 '<|vision_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151648 '<|box_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151646 '<|object_ref_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151649 '<|box_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151655 '<|image_pad|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151651 '<|quad_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151647 '<|object_ref_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151652 '<|vision_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151654 '<|vision_pad|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151656 '<|video_pad|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151644 '<|im_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151661 '<|fim_suffix|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151650 '<|quad_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: special tokens cache size = 22
Ιουν 23 16:12:57 brainiac ollama[116520]: load: token to piece cache size = 0.9310 MB
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: arch = qwen3
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab_only = 1
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model type = ?B
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model params = 7.57 B
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: general.name = Qwen3 Embedding 8B Bf16
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab type = BPE
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_vocab = 151665
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_merges = 151387
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: BOS token = 151643 '<|endoftext|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOS token = 151645 '<|im_end|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOT token = 151645 '<|im_end|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: PAD token = 151643 '<|endoftext|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: LF token = 198 'Ċ'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PRE token = 151659 '<|fim_prefix|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SUF token = 151661 '<|fim_suffix|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM MID token = 151660 '<|fim_middle|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PAD token = 151662 '<|fim_pad|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM REP token = 151663 '<|repo_name|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SEP token = 151664 '<|file_sep|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151643 '<|endoftext|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151645 '<|im_end|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151662 '<|fim_pad|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151663 '<|repo_name|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151664 '<|file_sep|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: max token length = 256
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_load: vocab only - skipping tensors
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=DEBUG source=server.go:360 msg="adding gpu library" path=/usr/local/lib/ollama/cuda_v12
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=DEBUG source=server.go:367 msg="adding gpu dependency paths" paths=[/usr/local/lib/ollama/cuda_v12]
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 --ctx-size 8192 --batch-size 512 --n-gpu-layers 37 --threads 8 --parallel 2 --port 43877"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=DEBUG source=server.go:432 msg=subprocess PATH=/home/nikolas/anaconda3/bin:/home/nikolas/anaconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=1 OLLAMA_MAX_LOADED_MODELS=3 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 LD_LIBRARY_PATH=/usr/local/lib/ollama/cuda_v12:/usr/local/lib/ollama/cuda_v12:/usr/local/lib/ollama:/usr/local/lib/ollama CUDA_VISIBLE_DEVICES=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=server.go:591 msg="waiting for llama runner to start responding"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.344+03:00 level=INFO source=runner.go:815 msg="starting go runner"
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.344+03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
Ιουν 23 16:12:57 brainiac ollama[116520]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-alderlake.so
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.349+03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12
Ιουν 23 16:12:57 brainiac ollama[116520]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
Ιουν 23 16:12:57 brainiac ollama[116520]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Ιουν 23 16:12:57 brainiac ollama[116520]: ggml_cuda_init: found 1 CUDA devices:
Ιουν 23 16:12:57 brainiac ollama[116520]: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
Ιουν 23 16:12:57 brainiac ollama[116520]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.387+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(gcc)
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.387+03:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:43877"
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090) - 20180 MiB free
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: loaded meta data with 27 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 (version GGUF V3 (latest))
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 0: general.architecture str = qwen3
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 1: general.type str = model
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B Bf16
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 4: general.size_label str = 8B
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 5: qwen3.block_count u32 = 36
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 6: qwen3.context_length u32 = 40960
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 7: qwen3.embedding_length u32 = 4096
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 12288
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 32
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 15: general.file_type u32 = 1
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 16: general.quantization_version u32 = 2
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 18: tokenizer.ggml.pre str = qwen2
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,151665] = ["!", """, "#", "$", "%", "&", "'", ...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 151645
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 151643
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = false
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 26: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f32: 145 tensors
Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f16: 253 tensors
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file format = GGUF V3 (latest)
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file type = F16
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file size = 14.10 GiB (16.00 BPW)
Ιουν 23 16:12:57 brainiac ollama[116520]: init_tokenizer: initializing tokenizer for type 2
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151660 '<|fim_middle|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151659 '<|fim_prefix|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151653 '<|vision_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151648 '<|box_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151646 '<|object_ref_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151649 '<|box_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151655 '<|image_pad|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151651 '<|quad_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151647 '<|object_ref_end|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151652 '<|vision_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151654 '<|vision_pad|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151656 '<|video_pad|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151644 '<|im_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151661 '<|fim_suffix|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151650 '<|quad_start|>' is not marked as EOG
Ιουν 23 16:12:57 brainiac ollama[116520]: load: special tokens cache size = 22
Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.586+03:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
Ιουν 23 16:12:57 brainiac ollama[116520]: load: token to piece cache size = 0.9310 MB
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: arch = qwen3
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab_only = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_ctx_train = 40960
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd = 4096
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_layer = 36
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_head = 32
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_head_kv = 8
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_rot = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_swa_pattern = 1
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_head_k = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_head_v = 128
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_gqa = 4
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_k_gqa = 1024
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_v_gqa = 1024
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_norm_eps = 0.0e+00
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_norm_rms_eps = 1.0e-06
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_clamp_kqv = 0.0e+00
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_max_alibi_bias = 0.0e+00
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_logit_scale = 0.0e+00
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_attn_scale = 0.0e+00
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_ff = 12288
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_expert = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_expert_used = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: causal attn = 1
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: pooling type = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: rope type = 2
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: rope scaling = linear
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: freq_base_train = 1000000.0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: freq_scale_train = 1
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_ctx_orig_yarn = 40960
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: rope_finetuned = unknown
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_d_conv = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_d_inner = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_d_state = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_dt_rank = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_dt_b_c_rms = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model type = 8B
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model params = 7.57 B
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: general.name = Qwen3 Embedding 8B Bf16
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab type = BPE
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_vocab = 151665
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_merges = 151387
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: BOS token = 151643 '<|endoftext|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOS token = 151645 '<|im_end|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOT token = 151645 '<|im_end|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: PAD token = 151643 '<|endoftext|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: LF token = 198 'Ċ'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PRE token = 151659 '<|fim_prefix|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SUF token = 151661 '<|fim_suffix|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM MID token = 151660 '<|fim_middle|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PAD token = 151662 '<|fim_pad|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM REP token = 151663 '<|repo_name|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SEP token = 151664 '<|file_sep|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151643 '<|endoftext|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151645 '<|im_end|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151662 '<|fim_pad|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151663 '<|repo_name|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151664 '<|file_sep|>'
Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: max token length = 256
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: loading model tensors, this can take a while... (mmap = true)
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 0 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 1 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 2 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 3 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 4 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 5 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 6 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 7 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 8 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 9 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 10 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 11 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 12 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 13 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 14 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 15 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 16 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 17 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 18 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 19 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 20 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 21 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 22 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 23 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 24 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 25 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 26 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 27 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 28 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 29 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 30 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 31 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 32 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 33 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 34 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 35 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 36 assigned to device CUDA0, is_swa = 0
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: tensor 'token_embd.weight' (f16) (and 0 others) cannot be used with preferred buffer type CUDA_Host, using CPU instead
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: offloading 36 repeating layers to GPU
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: offloading output layer to GPU
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: offloaded 37/37 layers to GPU
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: CUDA0 model buffer size = 14434.06 MiB
Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: CPU_Mapped model buffer size = 1184.88 MiB
Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.088+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.20"
Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.339+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.43"
Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.590+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.65"
Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.840+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.88"
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: constructing llama_context
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_seq_max = 2
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ctx = 8192
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ctx_per_seq = 4096
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_batch = 1024
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ubatch = 512
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: causal_attn = 1
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: flash_attn = 0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: freq_base = 1000000.0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: freq_scale = 1
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
Ιουν 23 16:12:58 brainiac ollama[116520]: set_abort_callback: call
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: CUDA_Host output buffer size = 1.19 MiB
Ιουν 23 16:12:58 brainiac ollama[116520]: create_memory: n_ctx = 8192 (padded)
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1, padding = 32
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 0: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 1: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 2: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 3: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 4: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 5: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 6: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 7: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 8: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 9: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 10: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 11: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 12: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 13: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 14: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 15: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 16: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 17: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 18: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 19: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 20: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 21: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 22: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 23: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 24: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 25: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 26: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 27: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 28: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 29: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 30: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 31: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 32: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 33: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 34: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 35: dev = CUDA0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: CUDA0 KV buffer size = 1152.00 MiB
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: KV self size = 1152.00 MiB, K (f16): 576.00 MiB, V (f16): 576.00 MiB
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: enumerating backends
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: backend_ptrs.size() = 2
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: max_nodes = 65536
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 0
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: reserving graph for n_tokens = 512, n_seqs = 1
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: reserving graph for n_tokens = 1, n_seqs = 1
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: reserving graph for n_tokens = 512, n_seqs = 1
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: CUDA0 compute buffer size = 560.00 MiB
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: CUDA_Host compute buffer size = 24.01 MiB
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: graph nodes = 1374
Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: graph splits = 2
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.091+03:00 level=INFO source=server.go:630 msg="llama runner started in 1.76 seconds"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.092+03:00 level=DEBUG source=sched.go:495 msg="finished setting up" runner.name=registry.ollama.ai/dengcao/Qwen3-Embedding-8B:F16 runner.inference=cuda runner.devices=1 runner.size="16.8 GiB" runner.vram="16.8 GiB" runner.parallel=2 runner.pid=117746 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 runner.num_ctx=8192
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.114+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.128+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=41 used=0 remaining=41
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.222+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=41 prompt=90 used=0 remaining=90
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.248+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=90 prompt=128 used=0 remaining=128
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.275+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=128 prompt=15 used=0 remaining=15
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.296+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=15 prompt=95 used=0 remaining=95
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.322+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=95 prompt=5 used=0 remaining=5
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.342+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=5 prompt=57 used=0 remaining=57
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.365+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=57 prompt=340 used=0 remaining=340
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.405+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=340 prompt=77 used=0 remaining=77
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.405+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.430+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=77 prompt=247 used=0 remaining=247
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.430+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.462+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=247 prompt=252 used=0 remaining=252
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.462+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.494+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=252 prompt=18 used=0 remaining=18
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.494+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.515+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=18 prompt=168 used=0 remaining=168
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.515+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.545+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=168 prompt=143 used=0 remaining=143
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.545+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.573+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=143 prompt=235 used=0 remaining=235
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.573+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.605+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=235 prompt=65 used=0 remaining=65
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.605+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.629+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=65 prompt=86 used=0 remaining=86
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.629+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.655+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=86 prompt=20 used=0 remaining=20
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.655+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.676+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=20 prompt=79 used=0 remaining=79
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.676+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.701+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=79 prompt=197 used=0 remaining=197
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.701+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.733+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=197 prompt=124 used=0 remaining=124
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.733+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.759+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=124 prompt=136 used=0 remaining=136
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.759+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.790+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=136 prompt=101 used=0 remaining=101
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.790+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.815+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=101 prompt=36 used=0 remaining=36
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.815+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.837+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=36 prompt=206 used=0 remaining=206
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.837+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.869+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=206 prompt=307 used=0 remaining=307
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.869+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.908+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=307 prompt=14 used=0 remaining=14
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.908+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.929+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=14 prompt=87 used=0 remaining=87
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.929+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.954+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=87 prompt=125 used=0 remaining=125
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.954+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
Ιουν 23 16:12:59 brainiac ollama[116520]: [GIN] 2025/06/23 - 16:12:59 | 500 | 3.075249638s | 10.0.20.178 | POST "/api/embed"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=DEBUG source=sched.go:503 msg="context for request finished"
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=DEBUG source=sched.go:343 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/dengcao/Qwen3-Embedding-8B:F16 runner.inference=cuda runner.devices=1 runner.size="16.8 GiB" runner.vram="16.8 GiB" runner.parallel=2 runner.pid=117746 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 runner.num_ctx=8192 duration=5m0s
Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=DEBUG source=sched.go:361 msg="after processing request finished event" runner.name=registry.ollama.ai/dengcao/Qwen3-Embedding-8B:F16 runner.inference=cuda runner.devices=1 runner.size="16.8 GiB" runner.vram="16.8 GiB" runner.parallel=2 runner.pid=117746 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 runner.num_ctx=8192 refCount=0

`

<!-- gh-comment-id:2996467327 --> @NikolasTh90 commented on GitHub (Jun 23, 2025): I am leaving my debug trace `Ιουν 23 16:12:49 brainiac ollama[116520]: CUDA driver version: 12.4 Ιουν 23 16:12:49 brainiac ollama[116520]: calling cuDeviceGetCount Ιουν 23 16:12:49 brainiac ollama[116520]: device count 1 Ιουν 23 16:12:49 brainiac ollama[116520]: time=2025-06-23T16:12:49.946+03:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=/usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01 Ιουν 23 16:12:50 brainiac ollama[116520]: [GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01] CUDA totalMem 23995mb Ιουν 23 16:12:50 brainiac ollama[116520]: [GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01] CUDA freeMem 20180mb Ιουν 23 16:12:50 brainiac ollama[116520]: [GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01] Compute Capability 8.9 Ιουν 23 16:12:50 brainiac ollama[116520]: time=2025-06-23T16:12:50.194+03:00 level=DEBUG source=amd_linux.go:419 msg="amdgpu driver not detected /sys/module/amdgpu" Ιουν 23 16:12:50 brainiac ollama[116520]: releasing cuda driver library Ιουν 23 16:12:50 brainiac ollama[116520]: time=2025-06-23T16:12:50.194+03:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="23.4 GiB" available="19.7 GiB" Ιουν 23 16:12:56 brainiac ollama[116520]: time=2025-06-23T16:12:56.932+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32 Ιουν 23 16:12:56 brainiac ollama[116520]: time=2025-06-23T16:12:56.932+03:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="188.5 GiB" before.free="181.1 GiB" before.free_swap="2.0 GiB" now.total="188.5 GiB" now.free="181.0 GiB" now.free_swap="2.0 GiB" Ιουν 23 16:12:56 brainiac ollama[116520]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuInit - 0x7cff1267ce20 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDriverGetVersion - 0x7cff1267ce40 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetCount - 0x7cff1267ce80 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGet - 0x7cff1267ce60 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetAttribute - 0x7cff1267cf60 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetUuid - 0x7cff1267cec0 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuDeviceGetName - 0x7cff1267cea0 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuCtxCreate_v3 - 0x7cff1267d140 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuMemGetInfo_v2 - 0x7cff12687080 Ιουν 23 16:12:56 brainiac ollama[116520]: dlsym: cuCtxDestroy - 0x7cff126e19c0 Ιουν 23 16:12:56 brainiac ollama[116520]: calling cuInit Ιουν 23 16:12:56 brainiac ollama[116520]: calling cuDriverGetVersion Ιουν 23 16:12:56 brainiac ollama[116520]: raw version 0x2f08 Ιουν 23 16:12:56 brainiac ollama[116520]: CUDA driver version: 12.4 Ιουν 23 16:12:56 brainiac ollama[116520]: calling cuDeviceGetCount Ιουν 23 16:12:56 brainiac ollama[116520]: device count 1 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.070+03:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="23.4 GiB" before.free="19.7 GiB" now.total="23.4 GiB" now.free="19.7 GiB" now.used="3.7 GiB" Ιουν 23 16:12:57 brainiac ollama[116520]: releasing cuda driver library Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.070+03:00 level=DEBUG source=sched.go:185 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.077+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.084+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.084+03:00 level=DEBUG source=sched.go:228 msg="loading first model" model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.084+03:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[19.7 GiB]" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.085+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=qwen3.vision.block_count default=0 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.085+03:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 gpu=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 parallel=2 available=21160460288 required="16.8 GiB" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.085+03:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="188.5 GiB" before.free="181.0 GiB" before.free_swap="2.0 GiB" now.total="188.5 GiB" now.free="181.0 GiB" now.free_swap="2.0 GiB" Ιουν 23 16:12:57 brainiac ollama[116520]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuInit - 0x7cff1267ce20 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDriverGetVersion - 0x7cff1267ce40 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetCount - 0x7cff1267ce80 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGet - 0x7cff1267ce60 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetAttribute - 0x7cff1267cf60 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetUuid - 0x7cff1267cec0 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuDeviceGetName - 0x7cff1267cea0 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuCtxCreate_v3 - 0x7cff1267d140 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuMemGetInfo_v2 - 0x7cff12687080 Ιουν 23 16:12:57 brainiac ollama[116520]: dlsym: cuCtxDestroy - 0x7cff126e19c0 Ιουν 23 16:12:57 brainiac ollama[116520]: calling cuInit Ιουν 23 16:12:57 brainiac ollama[116520]: calling cuDriverGetVersion Ιουν 23 16:12:57 brainiac ollama[116520]: raw version 0x2f08 Ιουν 23 16:12:57 brainiac ollama[116520]: CUDA driver version: 12.4 Ιουν 23 16:12:57 brainiac ollama[116520]: calling cuDeviceGetCount Ιουν 23 16:12:57 brainiac ollama[116520]: device count 1 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="23.4 GiB" before.free="19.7 GiB" now.total="23.4 GiB" now.free="19.7 GiB" now.used="3.7 GiB" Ιουν 23 16:12:57 brainiac ollama[116520]: releasing cuda driver library Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=INFO source=server.go:135 msg="system memory" total="188.5 GiB" free="181.0 GiB" free_swap="2.0 GiB" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[19.7 GiB]" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=qwen3.vision.block_count default=0 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=INFO source=server.go:168 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=37 layers.split="" memory.available="[19.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="16.8 GiB" memory.required.partial="16.8 GiB" memory.required.kv="1.1 GiB" memory.required.allocations="[16.8 GiB]" memory.weights.total="14.1 GiB" memory.weights.repeating="12.9 GiB" memory.weights.nonrepeating="1.2 GiB" memory.graph.full="768.0 MiB" memory.graph.partial="768.0 MiB" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.219+03:00 level=DEBUG source=server.go:284 msg="compatible gpu libraries" compatible="[cuda_v12 cuda_v11]" Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: loaded meta data with 27 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 (version GGUF V3 (latest)) Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 0: general.architecture str = qwen3 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 1: general.type str = model Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B Bf16 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 4: general.size_label str = 8B Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 5: qwen3.block_count u32 = 36 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 6: qwen3.context_length u32 = 40960 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 7: qwen3.embedding_length u32 = 4096 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 12288 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 32 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 15: general.file_type u32 = 1 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 16: general.quantization_version u32 = 2 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 18: tokenizer.ggml.pre str = qwen2 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,151665] = ["!", "\"", "#", "$", "%", "&", "'", ... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 151645 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 151643 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = false Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 26: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f32: 145 tensors Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f16: 253 tensors Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file format = GGUF V3 (latest) Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file type = F16 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file size = 14.10 GiB (16.00 BPW) Ιουν 23 16:12:57 brainiac ollama[116520]: init_tokenizer: initializing tokenizer for type 2 Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151660 '<|fim_middle|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151659 '<|fim_prefix|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151653 '<|vision_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151648 '<|box_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151646 '<|object_ref_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151649 '<|box_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151655 '<|image_pad|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151651 '<|quad_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151647 '<|object_ref_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151652 '<|vision_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151654 '<|vision_pad|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151656 '<|video_pad|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151644 '<|im_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151661 '<|fim_suffix|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151650 '<|quad_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: special tokens cache size = 22 Ιουν 23 16:12:57 brainiac ollama[116520]: load: token to piece cache size = 0.9310 MB Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: arch = qwen3 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab_only = 1 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model type = ?B Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model params = 7.57 B Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: general.name = Qwen3 Embedding 8B Bf16 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab type = BPE Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_vocab = 151665 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_merges = 151387 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: BOS token = 151643 '<|endoftext|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOS token = 151645 '<|im_end|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOT token = 151645 '<|im_end|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: PAD token = 151643 '<|endoftext|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: LF token = 198 'Ċ' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM MID token = 151660 '<|fim_middle|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM REP token = 151663 '<|repo_name|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SEP token = 151664 '<|file_sep|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151643 '<|endoftext|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151645 '<|im_end|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151662 '<|fim_pad|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151663 '<|repo_name|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151664 '<|file_sep|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: max token length = 256 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_load: vocab only - skipping tensors Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=DEBUG source=server.go:360 msg="adding gpu library" path=/usr/local/lib/ollama/cuda_v12 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=DEBUG source=server.go:367 msg="adding gpu dependency paths" paths=[/usr/local/lib/ollama/cuda_v12] Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 --ctx-size 8192 --batch-size 512 --n-gpu-layers 37 --threads 8 --parallel 2 --port 43877" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=DEBUG source=server.go:432 msg=subprocess PATH=/home/nikolas/anaconda3/bin:/home/nikolas/anaconda3/condabin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=1 OLLAMA_MAX_LOADED_MODELS=3 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 LD_LIBRARY_PATH=/usr/local/lib/ollama/cuda_v12:/usr/local/lib/ollama/cuda_v12:/usr/local/lib/ollama:/usr/local/lib/ollama CUDA_VISIBLE_DEVICES=GPU-dfea5d8a-bc26-58e4-88af-51bdaf629a01 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=server.go:591 msg="waiting for llama runner to start responding" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.335+03:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.344+03:00 level=INFO source=runner.go:815 msg="starting go runner" Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.344+03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama Ιουν 23 16:12:57 brainiac ollama[116520]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-alderlake.so Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.349+03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12 Ιουν 23 16:12:57 brainiac ollama[116520]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Ιουν 23 16:12:57 brainiac ollama[116520]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Ιουν 23 16:12:57 brainiac ollama[116520]: ggml_cuda_init: found 1 CUDA devices: Ιουν 23 16:12:57 brainiac ollama[116520]: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes Ιουν 23 16:12:57 brainiac ollama[116520]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.387+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(gcc) Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.387+03:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:43877" Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090) - 20180 MiB free Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: loaded meta data with 27 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 (version GGUF V3 (latest)) Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 0: general.architecture str = qwen3 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 1: general.type str = model Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B Bf16 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 4: general.size_label str = 8B Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 5: qwen3.block_count u32 = 36 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 6: qwen3.context_length u32 = 40960 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 7: qwen3.embedding_length u32 = 4096 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 12288 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 32 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 15: general.file_type u32 = 1 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 16: general.quantization_version u32 = 2 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 18: tokenizer.ggml.pre str = qwen2 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,151665] = ["!", "\"", "#", "$", "%", "&", "'", ... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 151645 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 151643 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643 Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 25: tokenizer.ggml.add_bos_token bool = false Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - kv 26: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f32: 145 tensors Ιουν 23 16:12:57 brainiac ollama[116520]: llama_model_loader: - type f16: 253 tensors Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file format = GGUF V3 (latest) Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file type = F16 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: file size = 14.10 GiB (16.00 BPW) Ιουν 23 16:12:57 brainiac ollama[116520]: init_tokenizer: initializing tokenizer for type 2 Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151660 '<|fim_middle|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151659 '<|fim_prefix|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151653 '<|vision_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151648 '<|box_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151646 '<|object_ref_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151649 '<|box_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151655 '<|image_pad|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151651 '<|quad_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151647 '<|object_ref_end|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151652 '<|vision_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151654 '<|vision_pad|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151656 '<|video_pad|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151644 '<|im_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151661 '<|fim_suffix|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: control token: 151650 '<|quad_start|>' is not marked as EOG Ιουν 23 16:12:57 brainiac ollama[116520]: load: special tokens cache size = 22 Ιουν 23 16:12:57 brainiac ollama[116520]: time=2025-06-23T16:12:57.586+03:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model" Ιουν 23 16:12:57 brainiac ollama[116520]: load: token to piece cache size = 0.9310 MB Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: arch = qwen3 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab_only = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_ctx_train = 40960 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd = 4096 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_layer = 36 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_head = 32 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_head_kv = 8 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_rot = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_swa_pattern = 1 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_head_k = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_head_v = 128 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_gqa = 4 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_k_gqa = 1024 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_embd_v_gqa = 1024 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_norm_eps = 0.0e+00 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_norm_rms_eps = 1.0e-06 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_clamp_kqv = 0.0e+00 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_max_alibi_bias = 0.0e+00 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_logit_scale = 0.0e+00 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: f_attn_scale = 0.0e+00 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_ff = 12288 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_expert = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_expert_used = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: causal attn = 1 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: pooling type = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: rope type = 2 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: rope scaling = linear Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: freq_base_train = 1000000.0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: freq_scale_train = 1 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_ctx_orig_yarn = 40960 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: rope_finetuned = unknown Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_d_conv = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_d_inner = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_d_state = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_dt_rank = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: ssm_dt_b_c_rms = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model type = 8B Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: model params = 7.57 B Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: general.name = Qwen3 Embedding 8B Bf16 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: vocab type = BPE Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_vocab = 151665 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: n_merges = 151387 Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: BOS token = 151643 '<|endoftext|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOS token = 151645 '<|im_end|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOT token = 151645 '<|im_end|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: PAD token = 151643 '<|endoftext|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: LF token = 198 'Ċ' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM MID token = 151660 '<|fim_middle|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM REP token = 151663 '<|repo_name|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: FIM SEP token = 151664 '<|file_sep|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151643 '<|endoftext|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151645 '<|im_end|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151662 '<|fim_pad|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151663 '<|repo_name|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: EOG token = 151664 '<|file_sep|>' Ιουν 23 16:12:57 brainiac ollama[116520]: print_info: max token length = 256 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: loading model tensors, this can take a while... (mmap = true) Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 0 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 1 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 2 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 3 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 4 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 5 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 6 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 7 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 8 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 9 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 10 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 11 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 12 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 13 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 14 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 15 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 16 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 17 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 18 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 19 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 20 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 21 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 22 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 23 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 24 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 25 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 26 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 27 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 28 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 29 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 30 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 31 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 32 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 33 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 34 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 35 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: layer 36 assigned to device CUDA0, is_swa = 0 Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: tensor 'token_embd.weight' (f16) (and 0 others) cannot be used with preferred buffer type CUDA_Host, using CPU instead Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: offloading 36 repeating layers to GPU Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: offloading output layer to GPU Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: offloaded 37/37 layers to GPU Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: CUDA0 model buffer size = 14434.06 MiB Ιουν 23 16:12:57 brainiac ollama[116520]: load_tensors: CPU_Mapped model buffer size = 1184.88 MiB Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.088+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.20" Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.339+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.43" Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.590+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.65" Ιουν 23 16:12:58 brainiac ollama[116520]: time=2025-06-23T16:12:58.840+03:00 level=DEBUG source=server.go:636 msg="model load progress 0.88" Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: constructing llama_context Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_seq_max = 2 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ctx = 8192 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ctx_per_seq = 4096 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_batch = 1024 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ubatch = 512 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: causal_attn = 1 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: flash_attn = 0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: freq_base = 1000000.0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: freq_scale = 1 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized Ιουν 23 16:12:58 brainiac ollama[116520]: set_abort_callback: call Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: CUDA_Host output buffer size = 1.19 MiB Ιουν 23 16:12:58 brainiac ollama[116520]: create_memory: n_ctx = 8192 (padded) Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1, padding = 32 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 0: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 1: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 2: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 3: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 4: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 5: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 6: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 7: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 8: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 9: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 10: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 11: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 12: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 13: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 14: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 15: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 16: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 17: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 18: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 19: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 20: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 21: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 22: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 23: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 24: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 25: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 26: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 27: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 28: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 29: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 30: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 31: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 32: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 33: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 34: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: layer 35: dev = CUDA0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: CUDA0 KV buffer size = 1152.00 MiB Ιουν 23 16:12:58 brainiac ollama[116520]: llama_kv_cache_unified: KV self size = 1152.00 MiB, K (f16): 576.00 MiB, V (f16): 576.00 MiB Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: enumerating backends Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: backend_ptrs.size() = 2 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: max_nodes = 65536 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 0 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: reserving graph for n_tokens = 512, n_seqs = 1 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: reserving graph for n_tokens = 1, n_seqs = 1 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: reserving graph for n_tokens = 512, n_seqs = 1 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: CUDA0 compute buffer size = 560.00 MiB Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: CUDA_Host compute buffer size = 24.01 MiB Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: graph nodes = 1374 Ιουν 23 16:12:58 brainiac ollama[116520]: llama_context: graph splits = 2 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.091+03:00 level=INFO source=server.go:630 msg="llama runner started in 1.76 seconds" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.092+03:00 level=DEBUG source=sched.go:495 msg="finished setting up" runner.name=registry.ollama.ai/dengcao/Qwen3-Embedding-8B:F16 runner.inference=cuda runner.devices=1 runner.size="16.8 GiB" runner.vram="16.8 GiB" runner.parallel=2 runner.pid=117746 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 runner.num_ctx=8192 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.114+03:00 level=DEBUG source=ggml.go:155 msg="key not found" key=general.alignment default=32 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.128+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=41 used=0 remaining=41 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.222+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=41 prompt=90 used=0 remaining=90 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.248+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=90 prompt=128 used=0 remaining=128 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.275+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=128 prompt=15 used=0 remaining=15 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.296+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=15 prompt=95 used=0 remaining=95 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.322+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=95 prompt=5 used=0 remaining=5 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.342+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=5 prompt=57 used=0 remaining=57 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.365+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=57 prompt=340 used=0 remaining=340 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.405+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=340 prompt=77 used=0 remaining=77 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.405+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.430+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=77 prompt=247 used=0 remaining=247 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.430+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.462+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=247 prompt=252 used=0 remaining=252 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.462+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.494+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=252 prompt=18 used=0 remaining=18 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.494+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.515+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=18 prompt=168 used=0 remaining=168 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.515+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.545+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=168 prompt=143 used=0 remaining=143 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.545+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.573+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=143 prompt=235 used=0 remaining=235 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.573+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.605+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=235 prompt=65 used=0 remaining=65 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.605+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.629+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=65 prompt=86 used=0 remaining=86 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.629+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.655+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=86 prompt=20 used=0 remaining=20 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.655+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.676+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=20 prompt=79 used=0 remaining=79 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.676+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.701+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=79 prompt=197 used=0 remaining=197 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.701+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.733+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=197 prompt=124 used=0 remaining=124 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.733+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.759+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=124 prompt=136 used=0 remaining=136 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.759+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.790+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=136 prompt=101 used=0 remaining=101 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.790+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.815+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=101 prompt=36 used=0 remaining=36 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.815+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.837+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=36 prompt=206 used=0 remaining=206 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.837+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.869+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=206 prompt=307 used=0 remaining=307 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.869+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.908+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=307 prompt=14 used=0 remaining=14 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.908+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.929+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=14 prompt=87 used=0 remaining=87 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.929+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.954+03:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=87 prompt=125 used=0 remaining=125 Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.954+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=INFO source=server.go:939 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" Ιουν 23 16:12:59 brainiac ollama[116520]: [GIN] 2025/06/23 - 16:12:59 | 500 | 3.075249638s | 10.0.20.178 | POST "/api/embed" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=DEBUG source=sched.go:503 msg="context for request finished" Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=DEBUG source=sched.go:343 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/dengcao/Qwen3-Embedding-8B:F16 runner.inference=cuda runner.devices=1 runner.size="16.8 GiB" runner.vram="16.8 GiB" runner.parallel=2 runner.pid=117746 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 runner.num_ctx=8192 duration=5m0s Ιουν 23 16:12:59 brainiac ollama[116520]: time=2025-06-23T16:12:59.981+03:00 level=DEBUG source=sched.go:361 msg="after processing request finished event" runner.name=registry.ollama.ai/dengcao/Qwen3-Embedding-8B:F16 runner.inference=cuda runner.devices=1 runner.size="16.8 GiB" runner.vram="16.8 GiB" runner.parallel=2 runner.pid=117746 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-01e070a939333b2a610ff7407ba016be0def3f804edce8958b879c8012e8f055 runner.num_ctx=8192 refCount=0 `

GiteaMirror commented 2026-04-22 12:55:59 -05:00

Author

Owner

Copy Link

@linabellbiu commented on GitHub (Jul 23, 2025):

I encountered the same problem.

(base) coke@coke:~/dify/docker$ journalctl -u ollama -f
7月 23 11:12:24 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:24 | 200 | 424.434928ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 200 | 441.649524ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 200 | 418.534893ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 200 | 397.615549ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:25 coke ollama[52538]: time=2025-07-23T11:12:25.802+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 500 | 496.054ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:26 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:26 | 200 | 521.802417ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:26 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:26 | 200 | 353.466301ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:12:26 coke ollama[52538]: time=2025-07-23T11:12:26.895+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:12:26 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:26 | 500 | 452.757032ms | 172.19.0.8 | POST "/api/embed"

7月 23 11:22:41 coke ollama[52538]: time=2025-07-23T11:22:41.980+08:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 gpu=GPU-6c63cf01-9a2d-4ccc-fbdd-e474b84adaae parallel=1 available=16599744512 required="5.9 GiB"
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.612+08:00 level=INFO source=server.go:135 msg="system memory" total="125.6 GiB" free="120.0 GiB" free_swap="8.0 GiB"
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.612+08:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=37 layers.split="" memory.available="[15.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.9 GiB" memory.required.partial="5.9 GiB" memory.required.kv="576.0 MiB" memory.required.allocations="[5.9 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="486.0 MiB" memory.graph.full="384.0 MiB" memory.graph.partial="384.0 MiB"
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 (version GGUF V3 (latest))
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 0: general.architecture str = qwen3
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 1: general.type str = model
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 4: general.size_label str = 8B
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 5: general.license str = apache-2.0
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 6: general.base_model.count u32 = 1
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 7: general.base_model.0.name str = Qwen3 8B Base
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 8: general.base_model.0.organization str = Qwen
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-8B-...
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 10: general.tags arr[str,5] = ["transformers", "sentence-transforme...
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 11: qwen3.block_count u32 = 36
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 12: qwen3.context_length u32 = 40960
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 13: qwen3.embedding_length u32 = 4096
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 14: qwen3.feed_forward_length u32 = 12288
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 15: qwen3.attention.head_count u32 = 32
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 16: qwen3.attention.head_count_kv u32 = 8
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 17: qwen3.rope.freq_base f32 = 1000000.000000
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 18: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 19: qwen3.attention.key_length u32 = 128
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 20: qwen3.attention.value_length u32 = 128
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 21: qwen3.pooling_type u32 = 3
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 23: tokenizer.ggml.pre str = qwen2
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,151665] = ["!", """, "#", "$", "%", "&", "'", ...
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 151643
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 28: tokenizer.ggml.padding_token_id u32 = 151643
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 29: tokenizer.ggml.eot_token_id u32 = 151645
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 34: general.quantization_version u32 = 2
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 35: general.file_type u32 = 15
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - type f32: 145 tensors
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - type q4_K: 216 tensors
7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - type q6_K: 37 tensors
7月 23 11:22:42 coke ollama[52538]: print_info: file format = GGUF V3 (latest)
7月 23 11:22:42 coke ollama[52538]: print_info: file type = Q4_K - Medium
7月 23 11:22:42 coke ollama[52538]: print_info: file size = 4.35 GiB (4.94 BPW)
7月 23 11:22:42 coke ollama[52538]: load: special tokens cache size = 22
7月 23 11:22:42 coke ollama[52538]: load: token to piece cache size = 0.9310 MB
7月 23 11:22:42 coke ollama[52538]: print_info: arch = qwen3
7月 23 11:22:42 coke ollama[52538]: print_info: vocab_only = 1
7月 23 11:22:42 coke ollama[52538]: print_info: model type = ?B
7月 23 11:22:42 coke ollama[52538]: print_info: model params = 7.57 B
7月 23 11:22:42 coke ollama[52538]: print_info: general.name = Qwen3 Embedding 8B
7月 23 11:22:42 coke ollama[52538]: print_info: vocab type = BPE
7月 23 11:22:42 coke ollama[52538]: print_info: n_vocab = 151665
7月 23 11:22:42 coke ollama[52538]: print_info: n_merges = 151387
7月 23 11:22:42 coke ollama[52538]: print_info: BOS token = 151643 '<|endoftext|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOS token = 151643 '<|endoftext|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOT token = 151645 '<|im_end|>'
7月 23 11:22:42 coke ollama[52538]: print_info: PAD token = 151643 '<|endoftext|>'
7月 23 11:22:42 coke ollama[52538]: print_info: LF token = 198 'Ċ'
7月 23 11:22:42 coke ollama[52538]: print_info: FIM PRE token = 151659 '<|fim_prefix|>'
7月 23 11:22:42 coke ollama[52538]: print_info: FIM SUF token = 151661 '<|fim_suffix|>'
7月 23 11:22:42 coke ollama[52538]: print_info: FIM MID token = 151660 '<|fim_middle|>'
7月 23 11:22:42 coke ollama[52538]: print_info: FIM PAD token = 151662 '<|fim_pad|>'
7月 23 11:22:42 coke ollama[52538]: print_info: FIM REP token = 151663 '<|repo_name|>'
7月 23 11:22:42 coke ollama[52538]: print_info: FIM SEP token = 151664 '<|file_sep|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151643 '<|endoftext|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151645 '<|im_end|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151662 '<|fim_pad|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151663 '<|repo_name|>'
7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151664 '<|file_sep|>'
7月 23 11:22:42 coke ollama[52538]: print_info: max token length = 256
7月 23 11:22:42 coke ollama[52538]: llama_model_load: vocab only - skipping tensors
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.911+08:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 --ctx-size 4096 --batch-size 512 --n-gpu-layers 37 --threads 36 --parallel 1 --port 39047"
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.912+08:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.912+08:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.912+08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.933+08:00 level=INFO source=runner.go:815 msg="starting go runner"
7月 23 11:22:43 coke ollama[52538]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
7月 23 11:22:43 coke ollama[52538]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
7月 23 11:22:43 coke ollama[52538]: ggml_cuda_init: found 1 CUDA devices:
7月 23 11:22:43 coke ollama[52538]: Device 0: Tesla V100-SXM2-16GB, compute capability 7.0, VMM: yes
7月 23 11:22:43 coke ollama[52538]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/libggml-cuda.so
7月 23 11:22:43 coke ollama[52538]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
7月 23 11:22:43 coke ollama[52538]: time=2025-07-23T11:22:43.044+08:00 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.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(gcc)
7月 23 11:22:43 coke ollama[52538]: time=2025-07-23T11:22:43.045+08:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:39047"
7月 23 11:22:43 coke ollama[52538]: time=2025-07-23T11:22:43.164+08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
7月 23 11:22:43 coke ollama[52538]: llama_model_load_from_file_impl: using device CUDA0 (Tesla V100-SXM2-16GB) - 15830 MiB free
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 (version GGUF V3 (latest))
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 0: general.architecture str = qwen3
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 1: general.type str = model
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 4: general.size_label str = 8B
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 5: general.license str = apache-2.0
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 6: general.base_model.count u32 = 1
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 7: general.base_model.0.name str = Qwen3 8B Base
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 8: general.base_model.0.organization str = Qwen
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-8B-...
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 10: general.tags arr[str,5] = ["transformers", "sentence-transforme...
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 11: qwen3.block_count u32 = 36
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 12: qwen3.context_length u32 = 40960
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 13: qwen3.embedding_length u32 = 4096
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 14: qwen3.feed_forward_length u32 = 12288
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 15: qwen3.attention.head_count u32 = 32
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 16: qwen3.attention.head_count_kv u32 = 8
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 17: qwen3.rope.freq_base f32 = 1000000.000000
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 18: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 19: qwen3.attention.key_length u32 = 128
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 20: qwen3.attention.value_length u32 = 128
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 21: qwen3.pooling_type u32 = 3
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 23: tokenizer.ggml.pre str = qwen2
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,151665] = ["!", """, "#", "$", "%", "&", "'", ...
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 151643
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 28: tokenizer.ggml.padding_token_id u32 = 151643
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 29: tokenizer.ggml.eot_token_id u32 = 151645
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 34: general.quantization_version u32 = 2
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 35: general.file_type u32 = 15
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - type f32: 145 tensors
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - type q4_K: 216 tensors
7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - type q6_K: 37 tensors
7月 23 11:22:43 coke ollama[52538]: print_info: file format = GGUF V3 (latest)
7月 23 11:22:43 coke ollama[52538]: print_info: file type = Q4_K - Medium
7月 23 11:22:43 coke ollama[52538]: print_info: file size = 4.35 GiB (4.94 BPW)
7月 23 11:22:43 coke ollama[52538]: load: special tokens cache size = 22
7月 23 11:22:43 coke ollama[52538]: load: token to piece cache size = 0.9310 MB
7月 23 11:22:43 coke ollama[52538]: print_info: arch = qwen3
7月 23 11:22:43 coke ollama[52538]: print_info: vocab_only = 0
7月 23 11:22:43 coke ollama[52538]: print_info: n_ctx_train = 40960
7月 23 11:22:43 coke ollama[52538]: print_info: n_embd = 4096
7月 23 11:22:43 coke ollama[52538]: print_info: n_layer = 36
7月 23 11:22:43 coke ollama[52538]: print_info: n_head = 32
7月 23 11:22:43 coke ollama[52538]: print_info: n_head_kv = 8
7月 23 11:22:43 coke ollama[52538]: print_info: n_rot = 128
7月 23 11:22:43 coke ollama[52538]: print_info: n_swa = 0
7月 23 11:22:43 coke ollama[52538]: print_info: n_swa_pattern = 1
7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_head_k = 128
7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_head_v = 128
7月 23 11:22:43 coke ollama[52538]: print_info: n_gqa = 4
7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_k_gqa = 1024
7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_v_gqa = 1024
7月 23 11:22:43 coke ollama[52538]: print_info: f_norm_eps = 0.0e+00
7月 23 11:22:43 coke ollama[52538]: print_info: f_norm_rms_eps = 1.0e-06
7月 23 11:22:43 coke ollama[52538]: print_info: f_clamp_kqv = 0.0e+00
7月 23 11:22:43 coke ollama[52538]: print_info: f_max_alibi_bias = 0.0e+00
7月 23 11:22:43 coke ollama[52538]: print_info: f_logit_scale = 0.0e+00
7月 23 11:22:43 coke ollama[52538]: print_info: f_attn_scale = 0.0e+00
7月 23 11:22:43 coke ollama[52538]: print_info: n_ff = 12288
7月 23 11:22:43 coke ollama[52538]: print_info: n_expert = 0
7月 23 11:22:43 coke ollama[52538]: print_info: n_expert_used = 0
7月 23 11:22:43 coke ollama[52538]: print_info: causal attn = 1
7月 23 11:22:43 coke ollama[52538]: print_info: pooling type = 0
7月 23 11:22:43 coke ollama[52538]: print_info: rope type = 2
7月 23 11:22:43 coke ollama[52538]: print_info: rope scaling = linear
7月 23 11:22:43 coke ollama[52538]: print_info: freq_base_train = 1000000.0
7月 23 11:22:43 coke ollama[52538]: print_info: freq_scale_train = 1
7月 23 11:22:43 coke ollama[52538]: print_info: n_ctx_orig_yarn = 40960
7月 23 11:22:43 coke ollama[52538]: print_info: rope_finetuned = unknown
7月 23 11:22:43 coke ollama[52538]: print_info: ssm_d_conv = 0
7月 23 11:22:43 coke ollama[52538]: print_info: ssm_d_inner = 0
7月 23 11:22:43 coke ollama[52538]: print_info: ssm_d_state = 0
7月 23 11:22:43 coke ollama[52538]: print_info: ssm_dt_rank = 0
7月 23 11:22:43 coke ollama[52538]: print_info: ssm_dt_b_c_rms = 0
7月 23 11:22:43 coke ollama[52538]: print_info: model type = 8B
7月 23 11:22:43 coke ollama[52538]: print_info: model params = 7.57 B
7月 23 11:22:43 coke ollama[52538]: print_info: general.name = Qwen3 Embedding 8B
7月 23 11:22:43 coke ollama[52538]: print_info: vocab type = BPE
7月 23 11:22:43 coke ollama[52538]: print_info: n_vocab = 151665
7月 23 11:22:43 coke ollama[52538]: print_info: n_merges = 151387
7月 23 11:22:43 coke ollama[52538]: print_info: BOS token = 151643 '<|endoftext|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOS token = 151643 '<|endoftext|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOT token = 151645 '<|im_end|>'
7月 23 11:22:43 coke ollama[52538]: print_info: PAD token = 151643 '<|endoftext|>'
7月 23 11:22:43 coke ollama[52538]: print_info: LF token = 198 'Ċ'
7月 23 11:22:43 coke ollama[52538]: print_info: FIM PRE token = 151659 '<|fim_prefix|>'
7月 23 11:22:43 coke ollama[52538]: print_info: FIM SUF token = 151661 '<|fim_suffix|>'
7月 23 11:22:43 coke ollama[52538]: print_info: FIM MID token = 151660 '<|fim_middle|>'
7月 23 11:22:43 coke ollama[52538]: print_info: FIM PAD token = 151662 '<|fim_pad|>'
7月 23 11:22:43 coke ollama[52538]: print_info: FIM REP token = 151663 '<|repo_name|>'
7月 23 11:22:43 coke ollama[52538]: print_info: FIM SEP token = 151664 '<|file_sep|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151643 '<|endoftext|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151645 '<|im_end|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151662 '<|fim_pad|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151663 '<|repo_name|>'
7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151664 '<|file_sep|>'
7月 23 11:22:43 coke ollama[52538]: print_info: max token length = 256
7月 23 11:22:43 coke ollama[52538]: load_tensors: loading model tensors, this can take a while... (mmap = true)
7月 23 11:22:43 coke ollama[52538]: load_tensors: offloading 36 repeating layers to GPU
7月 23 11:22:43 coke ollama[52538]: load_tensors: offloading output layer to GPU
7月 23 11:22:43 coke ollama[52538]: load_tensors: offloaded 37/37 layers to GPU
7月 23 11:22:43 coke ollama[52538]: load_tensors: CUDA0 model buffer size = 4454.48 MiB
7月 23 11:22:43 coke ollama[52538]: load_tensors: CPU_Mapped model buffer size = 485.99 MiB
7月 23 11:22:44 coke ollama[52538]: llama_context: constructing llama_context
7月 23 11:22:44 coke ollama[52538]: llama_context: n_seq_max = 1
7月 23 11:22:44 coke ollama[52538]: llama_context: n_ctx = 4096
7月 23 11:22:44 coke ollama[52538]: llama_context: n_ctx_per_seq = 4096
7月 23 11:22:44 coke ollama[52538]: llama_context: n_batch = 512
7月 23 11:22:44 coke ollama[52538]: llama_context: n_ubatch = 512
7月 23 11:22:44 coke ollama[52538]: llama_context: causal_attn = 1
7月 23 11:22:44 coke ollama[52538]: llama_context: flash_attn = 0
7月 23 11:22:44 coke ollama[52538]: llama_context: freq_base = 1000000.0
7月 23 11:22:44 coke ollama[52538]: llama_context: freq_scale = 1
7月 23 11:22:44 coke ollama[52538]: llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
7月 23 11:22:44 coke ollama[52538]: llama_context: CUDA_Host output buffer size = 0.59 MiB
7月 23 11:22:44 coke ollama[52538]: llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1, padding = 32
7月 23 11:22:44 coke ollama[52538]: llama_kv_cache_unified: CUDA0 KV buffer size = 576.00 MiB
7月 23 11:22:44 coke ollama[52538]: llama_kv_cache_unified: KV self size = 576.00 MiB, K (f16): 288.00 MiB, V (f16): 288.00 MiB
7月 23 11:22:44 coke ollama[52538]: llama_context: CUDA0 compute buffer size = 304.22 MiB
7月 23 11:22:44 coke ollama[52538]: llama_context: CUDA_Host compute buffer size = 16.01 MiB
7月 23 11:22:44 coke ollama[52538]: llama_context: graph nodes = 1374
7月 23 11:22:44 coke ollama[52538]: llama_context: graph splits = 2
7月 23 11:22:44 coke ollama[52538]: time=2025-07-23T11:22:44.672+08:00 level=INFO source=server.go:637 msg="llama runner started in 1.76 seconds"
7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 3.95730585s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.097434459s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.307573308s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.669465537s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.804644006s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 4.904773446s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.134000884s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.228851286s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.341684237s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.400859549s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 1.689496291s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 1.678098205s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.686379843s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.538931326s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.724966529s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.917776609s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 1.956736046s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.012959536s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.188382936s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.246491936s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.135688918s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.120466654s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.121280637s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.061815222s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.023892558s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 1.85088303s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.8030479s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.987750466s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.946864034s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.931853169s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 2.015723593s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.989309472s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.922490633s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 2.0567454s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.868851876s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.967369102s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 2.014157439s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.678476458s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.818347551s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.827386364s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.958683725s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 1.964767401s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.147872275s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.002911678s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.106361414s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.020523508s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.986329621s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 2.157722921s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 2.056154139s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.898146904s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.750018525s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.792368105s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.682409342s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.729942534s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.718403339s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.806173898s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.835032129s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 1.956552307s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 1.838304157s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 2.117775535s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 2.065336634s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.059879619s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.182850753s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.242307876s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.057612019s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.050148604s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.066062286s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.05169877s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.259331386s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.146808913s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.157495167s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.169183221s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.045220267s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.08916033s | 172.19.0.8 | POST "/api/embed"
7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.271678594s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 2.242806503s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 2.206771551s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 2.112279391s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 1.972523275s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 1.966753362s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 1.968742495s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 2.111598758s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 2.118126409s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 2.12256577s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.137052163s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 1.977210664s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.129386198s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.104305861s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.25898748s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.22796644s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.377335482s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.229183565s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.144004666s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.045762367s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.096489163s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.397861259s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.294938882s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.270212051s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.093897672s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.133588129s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 1.89427208s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.020326876s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.108986163s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 2.15937526s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 2.10358666s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 1.954297774s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 1.918591215s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.067281978s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.079225175s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 1.906419489s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.09282623s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.037115116s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 1.929813435s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 1.904462873s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 1.920355956s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 2.026594488s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 2.182131606s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.057251869s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.084850578s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.377947553s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.375754502s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 200 | 2.386479444s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 200 | 2.4657119s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:10 coke ollama[52538]: time=2025-07-23T11:23:10.549+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 500 | 2.471647682s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:10 coke ollama[52538]: time=2025-07-23T11:23:10.761+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 500 | 2.451126228s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:10 coke ollama[52538]: time=2025-07-23T11:23:10.929+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 500 | 2.297690143s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.201706198s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.353981302s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.377790703s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.177294558s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 2.189870298s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 2.099538443s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 2.103157126s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 1.520879897s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 1.312047266s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 200 | 1.325906987s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:13 coke ollama[52538]: time=2025-07-23T11:23:13.390+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 500 | 1.485435986s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:13 coke ollama[52538]: time=2025-07-23T11:23:13.652+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 500 | 1.518564149s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 200 | 1.515248278s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.524962098s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.483078572s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.531772122s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.5405692s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 995.409951ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 200 | 983.57271ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 200 | 1.011495537s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:15 coke ollama[52538]: time=2025-07-23T11:23:15.515+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 500 | 1.061746777s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 200 | 1.020969104s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:15 coke ollama[52538]: time=2025-07-23T11:23:15.984+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 500 | 1.086227525s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 1.076547889s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 1.092751771s | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 870.377521ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 629.196721ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 569.56616ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 577.025258ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 474.75144ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 426.562036ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 391.478256ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 517.016915ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 577.389127ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:18 coke ollama[52538]: time=2025-07-23T11:23:18.339+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 500 | 656.875998ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 647.499798ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 677.261687ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 336.855412ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 287.985336ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 429.927135ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 480.333425ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 402.479508ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 371.925804ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 395.811701ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 423.629679ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 393.455793ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 371.444651ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 382.807879ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 388.908937ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 267.030666ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 338.740995ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 496.115634ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 200 | 349.800447ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 200 | 385.33025ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 200 | 474.095746ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:22 coke ollama[52538]: time=2025-07-23T11:23:22.886+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 500 | 505.948694ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:23 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:23 | 200 | 499.55023ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:23 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:23 | 200 | 354.626686ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:23 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:23 | 200 | 338.116327ms | 172.19.0.8 | POST "/api/embed"
7月 23 11:23:24 coke ollama[52538]: time=2025-07-23T11:23:24.328+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"
7月 23 11:23:24 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:24 | 500 | 452.260564ms | 172.19.0.8 | POST "/api/embed"

<!-- gh-comment-id:3105539484 --> @linabellbiu commented on GitHub (Jul 23, 2025): I encountered the same problem. (base) coke@coke:~/dify/docker$ journalctl -u ollama -f 7月 23 11:12:24 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:24 | 200 | 424.434928ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 200 | 441.649524ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 200 | 418.534893ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 200 | 397.615549ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:25 coke ollama[52538]: time=2025-07-23T11:12:25.802+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:12:25 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:25 | 500 | 496.054ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:26 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:26 | 200 | 521.802417ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:26 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:26 | 200 | 353.466301ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:12:26 coke ollama[52538]: time=2025-07-23T11:12:26.895+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:12:26 coke ollama[52538]: [GIN] 2025/07/23 - 11:12:26 | 500 | 452.757032ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:41 coke ollama[52538]: time=2025-07-23T11:22:41.980+08:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 gpu=GPU-6c63cf01-9a2d-4ccc-fbdd-e474b84adaae parallel=1 available=16599744512 required="5.9 GiB" 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.612+08:00 level=INFO source=server.go:135 msg="system memory" total="125.6 GiB" free="120.0 GiB" free_swap="8.0 GiB" 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.612+08:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=37 layers.split="" memory.available="[15.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.9 GiB" memory.required.partial="5.9 GiB" memory.required.kv="576.0 MiB" memory.required.allocations="[5.9 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="486.0 MiB" memory.graph.full="384.0 MiB" memory.graph.partial="384.0 MiB" 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 (version GGUF V3 (latest)) 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 0: general.architecture str = qwen3 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 1: general.type str = model 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 4: general.size_label str = 8B 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 5: general.license str = apache-2.0 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 6: general.base_model.count u32 = 1 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 7: general.base_model.0.name str = Qwen3 8B Base 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 8: general.base_model.0.organization str = Qwen 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-8B-... 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 10: general.tags arr[str,5] = ["transformers", "sentence-transforme... 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 11: qwen3.block_count u32 = 36 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 12: qwen3.context_length u32 = 40960 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 13: qwen3.embedding_length u32 = 4096 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 14: qwen3.feed_forward_length u32 = 12288 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 15: qwen3.attention.head_count u32 = 32 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 16: qwen3.attention.head_count_kv u32 = 8 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 17: qwen3.rope.freq_base f32 = 1000000.000000 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 18: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 19: qwen3.attention.key_length u32 = 128 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 20: qwen3.attention.value_length u32 = 128 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 21: qwen3.pooling_type u32 = 3 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 23: tokenizer.ggml.pre str = qwen2 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,151665] = ["!", "\"", "#", "$", "%", "&", "'", ... 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 151643 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 28: tokenizer.ggml.padding_token_id u32 = 151643 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 29: tokenizer.ggml.eot_token_id u32 = 151645 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 34: general.quantization_version u32 = 2 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - kv 35: general.file_type u32 = 15 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - type f32: 145 tensors 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - type q4_K: 216 tensors 7月 23 11:22:42 coke ollama[52538]: llama_model_loader: - type q6_K: 37 tensors 7月 23 11:22:42 coke ollama[52538]: print_info: file format = GGUF V3 (latest) 7月 23 11:22:42 coke ollama[52538]: print_info: file type = Q4_K - Medium 7月 23 11:22:42 coke ollama[52538]: print_info: file size = 4.35 GiB (4.94 BPW) 7月 23 11:22:42 coke ollama[52538]: load: special tokens cache size = 22 7月 23 11:22:42 coke ollama[52538]: load: token to piece cache size = 0.9310 MB 7月 23 11:22:42 coke ollama[52538]: print_info: arch = qwen3 7月 23 11:22:42 coke ollama[52538]: print_info: vocab_only = 1 7月 23 11:22:42 coke ollama[52538]: print_info: model type = ?B 7月 23 11:22:42 coke ollama[52538]: print_info: model params = 7.57 B 7月 23 11:22:42 coke ollama[52538]: print_info: general.name = Qwen3 Embedding 8B 7月 23 11:22:42 coke ollama[52538]: print_info: vocab type = BPE 7月 23 11:22:42 coke ollama[52538]: print_info: n_vocab = 151665 7月 23 11:22:42 coke ollama[52538]: print_info: n_merges = 151387 7月 23 11:22:42 coke ollama[52538]: print_info: BOS token = 151643 '<|endoftext|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOS token = 151643 '<|endoftext|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOT token = 151645 '<|im_end|>' 7月 23 11:22:42 coke ollama[52538]: print_info: PAD token = 151643 '<|endoftext|>' 7月 23 11:22:42 coke ollama[52538]: print_info: LF token = 198 'Ċ' 7月 23 11:22:42 coke ollama[52538]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' 7月 23 11:22:42 coke ollama[52538]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' 7月 23 11:22:42 coke ollama[52538]: print_info: FIM MID token = 151660 '<|fim_middle|>' 7月 23 11:22:42 coke ollama[52538]: print_info: FIM PAD token = 151662 '<|fim_pad|>' 7月 23 11:22:42 coke ollama[52538]: print_info: FIM REP token = 151663 '<|repo_name|>' 7月 23 11:22:42 coke ollama[52538]: print_info: FIM SEP token = 151664 '<|file_sep|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151643 '<|endoftext|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151645 '<|im_end|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151662 '<|fim_pad|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151663 '<|repo_name|>' 7月 23 11:22:42 coke ollama[52538]: print_info: EOG token = 151664 '<|file_sep|>' 7月 23 11:22:42 coke ollama[52538]: print_info: max token length = 256 7月 23 11:22:42 coke ollama[52538]: llama_model_load: vocab only - skipping tensors 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.911+08:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 --ctx-size 4096 --batch-size 512 --n-gpu-layers 37 --threads 36 --parallel 1 --port 39047" 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.912+08:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.912+08:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.912+08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" 7月 23 11:22:42 coke ollama[52538]: time=2025-07-23T11:22:42.933+08:00 level=INFO source=runner.go:815 msg="starting go runner" 7月 23 11:22:43 coke ollama[52538]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no 7月 23 11:22:43 coke ollama[52538]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no 7月 23 11:22:43 coke ollama[52538]: ggml_cuda_init: found 1 CUDA devices: 7月 23 11:22:43 coke ollama[52538]: Device 0: Tesla V100-SXM2-16GB, compute capability 7.0, VMM: yes 7月 23 11:22:43 coke ollama[52538]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/libggml-cuda.so 7月 23 11:22:43 coke ollama[52538]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so 7月 23 11:22:43 coke ollama[52538]: time=2025-07-23T11:22:43.044+08:00 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.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(gcc) 7月 23 11:22:43 coke ollama[52538]: time=2025-07-23T11:22:43.045+08:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:39047" 7月 23 11:22:43 coke ollama[52538]: time=2025-07-23T11:22:43.164+08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" 7月 23 11:22:43 coke ollama[52538]: llama_model_load_from_file_impl: using device CUDA0 (Tesla V100-SXM2-16GB) - 15830 MiB free 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: loaded meta data with 36 key-value pairs and 398 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-3fcd3febec8b3fd64435204db75bf0dd73b91e8d0661e0331acfe7e7c3120b85 (version GGUF V3 (latest)) 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 0: general.architecture str = qwen3 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 1: general.type str = model 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 2: general.name str = Qwen3 Embedding 8B 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 3: general.basename str = Qwen3-Embedding 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 4: general.size_label str = 8B 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 5: general.license str = apache-2.0 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 6: general.base_model.count u32 = 1 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 7: general.base_model.0.name str = Qwen3 8B Base 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 8: general.base_model.0.organization str = Qwen 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-8B-... 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 10: general.tags arr[str,5] = ["transformers", "sentence-transforme... 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 11: qwen3.block_count u32 = 36 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 12: qwen3.context_length u32 = 40960 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 13: qwen3.embedding_length u32 = 4096 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 14: qwen3.feed_forward_length u32 = 12288 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 15: qwen3.attention.head_count u32 = 32 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 16: qwen3.attention.head_count_kv u32 = 8 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 17: qwen3.rope.freq_base f32 = 1000000.000000 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 18: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 19: qwen3.attention.key_length u32 = 128 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 20: qwen3.attention.value_length u32 = 128 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 21: qwen3.pooling_type u32 = 3 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 22: tokenizer.ggml.model str = gpt2 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 23: tokenizer.ggml.pre str = qwen2 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 24: tokenizer.ggml.tokens arr[str,151665] = ["!", "\"", "#", "$", "%", "&", "'", ... 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,151665] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 26: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 151643 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 28: tokenizer.ggml.padding_token_id u32 = 151643 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 29: tokenizer.ggml.eot_token_id u32 = 151645 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 34: general.quantization_version u32 = 2 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - kv 35: general.file_type u32 = 15 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - type f32: 145 tensors 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - type q4_K: 216 tensors 7月 23 11:22:43 coke ollama[52538]: llama_model_loader: - type q6_K: 37 tensors 7月 23 11:22:43 coke ollama[52538]: print_info: file format = GGUF V3 (latest) 7月 23 11:22:43 coke ollama[52538]: print_info: file type = Q4_K - Medium 7月 23 11:22:43 coke ollama[52538]: print_info: file size = 4.35 GiB (4.94 BPW) 7月 23 11:22:43 coke ollama[52538]: load: special tokens cache size = 22 7月 23 11:22:43 coke ollama[52538]: load: token to piece cache size = 0.9310 MB 7月 23 11:22:43 coke ollama[52538]: print_info: arch = qwen3 7月 23 11:22:43 coke ollama[52538]: print_info: vocab_only = 0 7月 23 11:22:43 coke ollama[52538]: print_info: n_ctx_train = 40960 7月 23 11:22:43 coke ollama[52538]: print_info: n_embd = 4096 7月 23 11:22:43 coke ollama[52538]: print_info: n_layer = 36 7月 23 11:22:43 coke ollama[52538]: print_info: n_head = 32 7月 23 11:22:43 coke ollama[52538]: print_info: n_head_kv = 8 7月 23 11:22:43 coke ollama[52538]: print_info: n_rot = 128 7月 23 11:22:43 coke ollama[52538]: print_info: n_swa = 0 7月 23 11:22:43 coke ollama[52538]: print_info: n_swa_pattern = 1 7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_head_k = 128 7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_head_v = 128 7月 23 11:22:43 coke ollama[52538]: print_info: n_gqa = 4 7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_k_gqa = 1024 7月 23 11:22:43 coke ollama[52538]: print_info: n_embd_v_gqa = 1024 7月 23 11:22:43 coke ollama[52538]: print_info: f_norm_eps = 0.0e+00 7月 23 11:22:43 coke ollama[52538]: print_info: f_norm_rms_eps = 1.0e-06 7月 23 11:22:43 coke ollama[52538]: print_info: f_clamp_kqv = 0.0e+00 7月 23 11:22:43 coke ollama[52538]: print_info: f_max_alibi_bias = 0.0e+00 7月 23 11:22:43 coke ollama[52538]: print_info: f_logit_scale = 0.0e+00 7月 23 11:22:43 coke ollama[52538]: print_info: f_attn_scale = 0.0e+00 7月 23 11:22:43 coke ollama[52538]: print_info: n_ff = 12288 7月 23 11:22:43 coke ollama[52538]: print_info: n_expert = 0 7月 23 11:22:43 coke ollama[52538]: print_info: n_expert_used = 0 7月 23 11:22:43 coke ollama[52538]: print_info: causal attn = 1 7月 23 11:22:43 coke ollama[52538]: print_info: pooling type = 0 7月 23 11:22:43 coke ollama[52538]: print_info: rope type = 2 7月 23 11:22:43 coke ollama[52538]: print_info: rope scaling = linear 7月 23 11:22:43 coke ollama[52538]: print_info: freq_base_train = 1000000.0 7月 23 11:22:43 coke ollama[52538]: print_info: freq_scale_train = 1 7月 23 11:22:43 coke ollama[52538]: print_info: n_ctx_orig_yarn = 40960 7月 23 11:22:43 coke ollama[52538]: print_info: rope_finetuned = unknown 7月 23 11:22:43 coke ollama[52538]: print_info: ssm_d_conv = 0 7月 23 11:22:43 coke ollama[52538]: print_info: ssm_d_inner = 0 7月 23 11:22:43 coke ollama[52538]: print_info: ssm_d_state = 0 7月 23 11:22:43 coke ollama[52538]: print_info: ssm_dt_rank = 0 7月 23 11:22:43 coke ollama[52538]: print_info: ssm_dt_b_c_rms = 0 7月 23 11:22:43 coke ollama[52538]: print_info: model type = 8B 7月 23 11:22:43 coke ollama[52538]: print_info: model params = 7.57 B 7月 23 11:22:43 coke ollama[52538]: print_info: general.name = Qwen3 Embedding 8B 7月 23 11:22:43 coke ollama[52538]: print_info: vocab type = BPE 7月 23 11:22:43 coke ollama[52538]: print_info: n_vocab = 151665 7月 23 11:22:43 coke ollama[52538]: print_info: n_merges = 151387 7月 23 11:22:43 coke ollama[52538]: print_info: BOS token = 151643 '<|endoftext|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOS token = 151643 '<|endoftext|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOT token = 151645 '<|im_end|>' 7月 23 11:22:43 coke ollama[52538]: print_info: PAD token = 151643 '<|endoftext|>' 7月 23 11:22:43 coke ollama[52538]: print_info: LF token = 198 'Ċ' 7月 23 11:22:43 coke ollama[52538]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' 7月 23 11:22:43 coke ollama[52538]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' 7月 23 11:22:43 coke ollama[52538]: print_info: FIM MID token = 151660 '<|fim_middle|>' 7月 23 11:22:43 coke ollama[52538]: print_info: FIM PAD token = 151662 '<|fim_pad|>' 7月 23 11:22:43 coke ollama[52538]: print_info: FIM REP token = 151663 '<|repo_name|>' 7月 23 11:22:43 coke ollama[52538]: print_info: FIM SEP token = 151664 '<|file_sep|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151643 '<|endoftext|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151645 '<|im_end|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151662 '<|fim_pad|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151663 '<|repo_name|>' 7月 23 11:22:43 coke ollama[52538]: print_info: EOG token = 151664 '<|file_sep|>' 7月 23 11:22:43 coke ollama[52538]: print_info: max token length = 256 7月 23 11:22:43 coke ollama[52538]: load_tensors: loading model tensors, this can take a while... (mmap = true) 7月 23 11:22:43 coke ollama[52538]: load_tensors: offloading 36 repeating layers to GPU 7月 23 11:22:43 coke ollama[52538]: load_tensors: offloading output layer to GPU 7月 23 11:22:43 coke ollama[52538]: load_tensors: offloaded 37/37 layers to GPU 7月 23 11:22:43 coke ollama[52538]: load_tensors: CUDA0 model buffer size = 4454.48 MiB 7月 23 11:22:43 coke ollama[52538]: load_tensors: CPU_Mapped model buffer size = 485.99 MiB 7月 23 11:22:44 coke ollama[52538]: llama_context: constructing llama_context 7月 23 11:22:44 coke ollama[52538]: llama_context: n_seq_max = 1 7月 23 11:22:44 coke ollama[52538]: llama_context: n_ctx = 4096 7月 23 11:22:44 coke ollama[52538]: llama_context: n_ctx_per_seq = 4096 7月 23 11:22:44 coke ollama[52538]: llama_context: n_batch = 512 7月 23 11:22:44 coke ollama[52538]: llama_context: n_ubatch = 512 7月 23 11:22:44 coke ollama[52538]: llama_context: causal_attn = 1 7月 23 11:22:44 coke ollama[52538]: llama_context: flash_attn = 0 7月 23 11:22:44 coke ollama[52538]: llama_context: freq_base = 1000000.0 7月 23 11:22:44 coke ollama[52538]: llama_context: freq_scale = 1 7月 23 11:22:44 coke ollama[52538]: llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized 7月 23 11:22:44 coke ollama[52538]: llama_context: CUDA_Host output buffer size = 0.59 MiB 7月 23 11:22:44 coke ollama[52538]: llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1, padding = 32 7月 23 11:22:44 coke ollama[52538]: llama_kv_cache_unified: CUDA0 KV buffer size = 576.00 MiB 7月 23 11:22:44 coke ollama[52538]: llama_kv_cache_unified: KV self size = 576.00 MiB, K (f16): 288.00 MiB, V (f16): 288.00 MiB 7月 23 11:22:44 coke ollama[52538]: llama_context: CUDA0 compute buffer size = 304.22 MiB 7月 23 11:22:44 coke ollama[52538]: llama_context: CUDA_Host compute buffer size = 16.01 MiB 7月 23 11:22:44 coke ollama[52538]: llama_context: graph nodes = 1374 7月 23 11:22:44 coke ollama[52538]: llama_context: graph splits = 2 7月 23 11:22:44 coke ollama[52538]: time=2025-07-23T11:22:44.672+08:00 level=INFO source=server.go:637 msg="llama runner started in 1.76 seconds" 7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 3.95730585s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.097434459s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.307573308s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.669465537s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:45 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:45 | 200 | 4.804644006s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 4.904773446s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.134000884s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.228851286s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.341684237s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 5.400859549s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 1.689496291s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:46 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:46 | 200 | 1.678098205s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.686379843s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.538931326s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.724966529s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:47 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:47 | 200 | 1.917776609s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 1.956736046s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.012959536s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.188382936s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.246491936s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:48 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:48 | 200 | 2.135688918s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.120466654s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.121280637s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.061815222s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 2.023892558s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:49 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:49 | 200 | 1.85088303s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.8030479s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.987750466s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.946864034s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 1.931853169s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:50 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:50 | 200 | 2.015723593s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.989309472s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.922490633s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 2.0567454s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.868851876s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:51 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:51 | 200 | 1.967369102s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 2.014157439s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.678476458s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.818347551s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.827386364s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:52 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:52 | 200 | 1.958683725s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 1.964767401s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.147872275s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.002911678s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.106361414s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:53 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:53 | 200 | 2.020523508s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.986329621s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 2.157722921s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 2.056154139s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.898146904s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.750018525s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:54 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:54 | 200 | 1.792368105s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.682409342s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.729942534s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.718403339s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.806173898s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:55 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:55 | 200 | 1.835032129s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 1.956552307s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 1.838304157s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 2.117775535s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:56 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:56 | 200 | 2.065336634s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.059879619s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.182850753s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.242307876s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.057612019s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:57 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:57 | 200 | 2.050148604s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.066062286s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.05169877s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.259331386s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:58 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:58 | 200 | 2.146808913s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.157495167s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.169183221s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.045220267s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.08916033s | 172.19.0.8 | POST "/api/embed" 7月 23 11:22:59 coke ollama[52538]: [GIN] 2025/07/23 - 11:22:59 | 200 | 2.271678594s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 2.242806503s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 2.206771551s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 2.112279391s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 1.972523275s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:00 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:00 | 200 | 1.966753362s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 1.968742495s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 2.111598758s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 2.118126409s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:01 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:01 | 200 | 2.12256577s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.137052163s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 1.977210664s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.129386198s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.104305861s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:02 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:02 | 200 | 2.25898748s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.22796644s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.377335482s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.229183565s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.144004666s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:03 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:03 | 200 | 2.045762367s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.096489163s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.397861259s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.294938882s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:04 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:04 | 200 | 2.270212051s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.093897672s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.133588129s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 1.89427208s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.020326876s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:05 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:05 | 200 | 2.108986163s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 2.15937526s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 2.10358666s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 1.954297774s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:06 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:06 | 200 | 1.918591215s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.067281978s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.079225175s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 1.906419489s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.09282623s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 2.037115116s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:07 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:07 | 200 | 1.929813435s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 1.904462873s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 1.920355956s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 2.026594488s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:08 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:08 | 200 | 2.182131606s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.057251869s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.084850578s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.377947553s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:09 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:09 | 200 | 2.375754502s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 200 | 2.386479444s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 200 | 2.4657119s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:10 coke ollama[52538]: time=2025-07-23T11:23:10.549+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 500 | 2.471647682s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:10 coke ollama[52538]: time=2025-07-23T11:23:10.761+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 500 | 2.451126228s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:10 coke ollama[52538]: time=2025-07-23T11:23:10.929+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:10 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:10 | 500 | 2.297690143s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.201706198s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.353981302s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.377790703s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:11 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:11 | 200 | 2.177294558s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 2.189870298s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 2.099538443s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 2.103157126s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 1.520879897s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:12 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:12 | 200 | 1.312047266s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 200 | 1.325906987s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:13 coke ollama[52538]: time=2025-07-23T11:23:13.390+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 500 | 1.485435986s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:13 coke ollama[52538]: time=2025-07-23T11:23:13.652+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 500 | 1.518564149s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:13 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:13 | 200 | 1.515248278s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.524962098s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.483078572s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.531772122s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 1.5405692s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:14 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:14 | 200 | 995.409951ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 200 | 983.57271ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 200 | 1.011495537s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:15 coke ollama[52538]: time=2025-07-23T11:23:15.515+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 500 | 1.061746777s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 200 | 1.020969104s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:15 coke ollama[52538]: time=2025-07-23T11:23:15.984+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:15 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:15 | 500 | 1.086227525s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 1.076547889s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 1.092751771s | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 870.377521ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:16 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:16 | 200 | 629.196721ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 569.56616ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 577.025258ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 474.75144ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 426.562036ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 391.478256ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:17 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:17 | 200 | 517.016915ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 577.389127ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:18 coke ollama[52538]: time=2025-07-23T11:23:18.339+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 500 | 656.875998ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 647.499798ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 677.261687ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:18 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:18 | 200 | 336.855412ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 287.985336ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 429.927135ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 480.333425ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:19 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:19 | 200 | 402.479508ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 371.925804ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 395.811701ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 423.629679ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 393.455793ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:20 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:20 | 200 | 371.444651ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 382.807879ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 388.908937ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 267.030666ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 338.740995ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:21 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:21 | 200 | 496.115634ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 200 | 349.800447ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 200 | 385.33025ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 200 | 474.095746ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:22 coke ollama[52538]: time=2025-07-23T11:23:22.886+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:22 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:22 | 500 | 505.948694ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:23 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:23 | 200 | 499.55023ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:23 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:23 | 200 | 354.626686ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:23 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:23 | 200 | 338.116327ms | 172.19.0.8 | POST "/api/embed" 7月 23 11:23:24 coke ollama[52538]: time=2025-07-23T11:23:24.328+08:00 level=INFO source=server.go:946 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" 7月 23 11:23:24 coke ollama[52538]: [GIN] 2025/07/23 - 11:23:24 | 500 | 452.260564ms | 172.19.0.8 | POST "/api/embed"

GiteaMirror commented 2026-04-22 12:56:00 -05:00

Author

Owner

Copy Link

@mcr-ksh commented on GitHub (Dec 24, 2025):

+1

just ran into this after updating the Ollama to the lastest 0.13.5. Used to work flawless in an n8n workflow.

Before the error I got:
"init: embeddings required but some input tokens were not marked as outputs -> overriding"

<!-- gh-comment-id:3689841252 --> @mcr-ksh commented on GitHub (Dec 24, 2025): +1 just ran into this after updating the Ollama to the lastest 0.13.5. Used to work flawless in an n8n workflow. Before the error I got: "init: embeddings required but some input tokens were not marked as outputs -> overriding"

GiteaMirror commented 2026-04-22 12:56:01 -05:00

Author

Owner

Copy Link

@nicho2 commented on GitHub (Jan 15, 2026):

I've ollama version 0.13.4

I just received this:

POST /api/embed HTTP/1.1
Host: 10.2.142.77:11434
User-Agent: python-requests/2.32.5
Accept-Encoding: gzip, deflate
Accept: */*
Connection: keep-alive
Content-Type: application/json
Content-Length: 202

{"input": ["This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such."], "model": "bge-m3:latest", "options": {"use_mmap": true}}


HTTP/1.1 500 Internal Server Error
Content-Type: application/json; charset=utf-8
Date: Thu, 15 Jan 2026 12:49:57 GMT
Content-Length: 67

{"error":"failed to encode response: json: unsupported value: NaN"}

-Log:

init: embeddings required but some input tokens were not marked as outputs -> overriding

[GIN] 2026/01/15 - 12:49:57 | 200 |  124.310228ms |      172.21.0.1 | POST     "/api/embed"

time=2026-01-15T12:49:57.196Z level=DEBUG source=sched.go:385 msg="context for request finished" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096

time=2026-01-15T12:49:57.197Z level=DEBUG source=sched.go:290 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 duration=8m0s

time=2026-01-15T12:49:57.197Z level=DEBUG source=sched.go:308 msg="after processing request finished event" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 refCount=0

time=2026-01-15T12:49:57.332Z level=DEBUG source=sched.go:626 msg="evaluating already loaded" model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c

time=2026-01-15T12:49:57.360Z level=DEBUG source=ggml.go:281 msg="key with type not found" key=general.alignment default=32

time=2026-01-15T12:49:57.362Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=359 prompt=29 used=0 remaining=29

decode: cannot decode batches with this context (calling encode() instead)

init: embeddings required but some input tokens were not marked as outputs -> overriding

time=2026-01-15T12:49:57.367Z level=INFO source=server.go:1724 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"

[GIN] 2026/01/15 - 12:49:57 | 500 |   129.39789ms |      172.21.0.1 | POST     "/api/embed"

time=2026-01-15T12:49:57.368Z level=DEBUG source=sched.go:385 msg="context for request finished" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096

time=2026-01-15T12:49:57.368Z level=DEBUG source=sched.go:290 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 duration=8m0s

time=2026-01-15T12:49:57.368Z level=DEBUG source=sched.go:308 msg="after processing request finished event" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 refCount=0

<!-- gh-comment-id:3754680330 --> @nicho2 commented on GitHub (Jan 15, 2026): I've ollama version 0.13.4 I just received this: POST /api/embed HTTP/1.1 Host: 10.2.142.77:11434 User-Agent: python-requests/2.32.5 Accept-Encoding: gzip, deflate Accept: */* Connection: keep-alive Content-Type: application/json Content-Length: 202 {"input": ["This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such."], "model": "bge-m3:latest", "options": {"use_mmap": true}} HTTP/1.1 500 Internal Server Error Content-Type: application/json; charset=utf-8 Date: Thu, 15 Jan 2026 12:49:57 GMT Content-Length: 67 {"error":"failed to encode response: json: unsupported value: NaN"} -Log: init: embeddings required but some input tokens were not marked as outputs -> overriding [GIN] 2026/01/15 - 12:49:57 | 200 | 124.310228ms | 172.21.0.1 | POST "/api/embed" time=2026-01-15T12:49:57.196Z level=DEBUG source=sched.go:385 msg="context for request finished" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 time=2026-01-15T12:49:57.197Z level=DEBUG source=sched.go:290 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 duration=8m0s time=2026-01-15T12:49:57.197Z level=DEBUG source=sched.go:308 msg="after processing request finished event" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 refCount=0 time=2026-01-15T12:49:57.332Z level=DEBUG source=sched.go:626 msg="evaluating already loaded" model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c time=2026-01-15T12:49:57.360Z level=DEBUG source=ggml.go:281 msg="key with type not found" key=general.alignment default=32 time=2026-01-15T12:49:57.362Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=359 prompt=29 used=0 remaining=29 decode: cannot decode batches with this context (calling encode() instead) init: embeddings required but some input tokens were not marked as outputs -> overriding time=2026-01-15T12:49:57.367Z level=INFO source=server.go:1724 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" [GIN] 2026/01/15 - 12:49:57 | 500 | 129.39789ms | 172.21.0.1 | POST "/api/embed" time=2026-01-15T12:49:57.368Z level=DEBUG source=sched.go:385 msg="context for request finished" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 time=2026-01-15T12:49:57.368Z level=DEBUG source=sched.go:290 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 duration=8m0s time=2026-01-15T12:49:57.368Z level=DEBUG source=sched.go:308 msg="after processing request finished event" runner.name=registry.ollama.ai/library/bge-m3:latest runner.inference="[{ID:GPU-45972459-815c-f304-9fdf-b952276c9b13 Library:CUDA}]" runner.size="1.1 GiB" runner.vram="1.1 GiB" runner.parallel=1 runner.pid=10997 runner.model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c runner.num_ctx=4096 refCount=0

GiteaMirror commented 2026-04-22 12:56:01 -05:00

Author

Owner

Copy Link

@nicho2 commented on GitHub (Jan 15, 2026):

same thing in 0.14.0

but

when i send :
curl http://10.2.142.77:11434/api/embed -d '{
"model": "bge-m3:latest",
"input": "This document is a draft distributed for approval."
}'
it's OK:

POST /api/embed HTTP/1.1
Host: 10.2.142.77:11434
User-Agent: curl/7.81.0
Accept: */*
Content-Length: 95
Content-Type: application/x-www-form-urlencoded

{
  "model": "bge-m3:latest",
  "input": "This document is a draft distributed for approval."
}
HTTP/1.1 200 OK
Content-Type: application/json; charset=utf-8
Date: Thu, 15 Jan 2026 13:16:49 GMT
Transfer-Encoding: chunked

{"model":"bge-m3:latest","embeddings":[[-0.015445454,0.003276025,-0.032736298,0.008763502,-0.0253346,-0.05621706,0.060042914,0.013629458,0.012102511,0.01625889,-0.0021870725,-0.01320955,-0.010680699,-0.00022075947,0.018077575,0.004602876,0.050414875,-0.02080775,-0.027023934,-0.002845781,-0.030523593,0.011803625,0.040470228,0.024725655,-0.047343507,0.022378556,-0.016207317,-0.001203077,0.03228503,0.02187892,0.018690186,-0.01785771,0.029428432,-0.024072818,0.0045784162,-0.044287648,-0.013129439,-0.033630155,-0.030983737,0.023344262,-0.012560762,-0.0078084823,0.021287857,-0.061550602,0.019530142,0.011605382,0.00019195586,-0.022348104,-0.025308289,-0.0028609901,-0.031649172,0.023210876,0.056044046,-0.026173636,0.02812822,0.0037022,0.021429488,-0.019578056,-0.0845583,0.023569038,-0.044206563,-0.0113979485,-0.0103847,-0.008856806,0.020307465,0.06085907,0.048012324,0.009598146,-0.024038533,-0.017801082,-0.008899206,0.032167103,-0.02682478,0.0007035052,-0.056625433,0.021817239,0.032399602,-0.07642074,0.0036620772,0.058536515,0.008637845,-0.009830092,0.01197731,0.007796856,-0.054444678,-0.0076599023,-0.047528476,0.039386824,0.019119918,-0.009168872,-0.034833595,0.015555431,0.036482897,-0.026195176,-0.03490326,0.01288963,-0.076935954,-0.004761672,0.0074276295,0.013270374,0.027959965,0.021551395,-0.009471928,-0.010893856,0.002629465,-0.019170653,0.039675627,0.011736331,0.04628006,-0.008328642,-0.011577215,0.005860599,0.033464115,-0.018660733,0.01838674,-0.007907991,-0.016121991,-0.03981626,-0.015577496,-0.0021521072,0.0028034544,0.0076389913,0.049580887,-0.029046664,0.013811698,-0.048230592,0.019610893,0.039051075,0.0260056,-0.014266633,0.04694729,0.064460024,-0.014719029,-0.023613526,-0.032929454,-0.02090901,-0.03304115,0.021721477,0.0021194443,-0.034874875,0.07790756,0.012337135,-0.045040157,-0.026725331,0.057313863,-0.1025184,0.038194004,-0.01808049,0.03202347,0.004171357,0.014145894,0.022467604,0.0084766345,-0.0104922885,0.05689718,-0.03424302,0.015268611,0.019957358,0.0132919345,0.06806766,-0.028033918,0.029516596,-0.017997397,-0.020068994,-0.0009792305,0.01766953,0.029603066,0.06188093,-0.010562154,-0.06265268,-0.000027546368,-0.0031017687,0.04113726,-0.022804378,0.01585459,0.026730621,0.047201797,-0.0032959513,0.0022920186,-0.05411061,-0.019644663,0.031293236,-0.012883818,-0.026349872,-0.008244882,-0.00010930865,0.011371867,-0.020588009,-0.012020719,-0.02025077,-0.021215668,-0.032841977,0.0034183662,0.001374491,-0.009573052,-0.025447372,-0.027364759,-0.048350755,-0.010890413,-0.068638876,-0.026589585,0.029143576,0.07048744,0.0071354685,-0.014211876,-0.026391614,-0.027603779,-0.028470699,0.017523188,-0.040969852,-0.057280704,-0.0020852506,-0.0043937746,-0.011291085,-0.011979187,0.034178134,0.028641421,0.011618161,0.010678629,-0.030960325,-0.032818086,0.007113562,0.021895787,0.058146212,0.009214191,0.005038449,-0.007188165,0.024632165,0.031550083,-0.057382002,-0.039669264,-0.0020119057,-0.019224258,-0.040861137,0.07563455,0.0095492825,-0.014664481,0.024950933,0.018580398,0.005288304,-0.012328877,0.0102612525,0.0119015025,-0.03538505,-0.04062535,0.029592982,-0.034370214,0.029243223,-0.03107611,-0.0019364593,0.023855047,-0.0009654886,-0.03617323,0.025261872,0.0060371687,0.01842621,-0.017190982,-0.0027674527,0.006770897,-0.0065281377,0.023136081,-0.03553879,0.01712718,0.03552223,0.036402587,-0.01579471,-0.033217978,0.011281189,0.030687224,-0.053479318,0.003708311,-0.026924105,0.016295,-0.015588822,0.034735266,-0.0038257819,-0.0133855445,-0.0045978953,0.036552515,-0.019900836,-0.016232884,0.048368648,0.026970956,-0.013713893,0.030491758,0.006877708,-0.008417689,-0.021315278,0.036123082,-0.011471454,-0.01975225,-0.004748489,0.058369484,-0.021009754,-0.023229802,0.01102451,-0.0082925875,-0.16528273,0.00863624,-0.004970701,-0.031583283,0.0069563654,-0.018628025,-0.035674002,-0.013911859,-0.000086524225,0.053010687,0.035070438,-0.04878839,0.018753966,0.037815135,0.01555174,0.015058085,-0.008200825,0.0029965467,-0.00072948914,0.00010433371,-0.02442157,-0.021330282,0.10416154,0.0069224103,-0.041053694,0.016387695,0.037728645,0.0024058563,-0.042805858,0.026593184,0.008263658,0.009043465,-0.0067615905,0.0076865233,-0.0040431404,0.040152516,0.05020241,-0.011230476,-0.020675005,-0.021936446,0.01432799,0.03975448,-0.016602222,0.03745323,-0.0051519643,-0.00832569,0.020547722,0.0022187612,-0.019729288,-0.009041786,-0.006680888,-0.012119521,-0.02245279,-0.011801761,-0.07318276,-0.008810027,-0.043800347,0.01201429,-0.052644923,0.055857368,-0.024241354,-0.061781283,0.021951046,-0.00045822386,-0.038456485,-0.00041926446,0.04600639,-0.011969451,0.0047146957,-0.015729569,0.023674335,-0.017260734,0.03086358,-0.022705378,0.017492127,0.023114882,0.0075497935,0.008272093,-0.031016277,-0.09495582,0.010780377,0.0034350043,-0.011891655,-0.016835637,-0.025169417,-0.017145382,-0.0024130016,0.005594143,0.08055568,0.25624886,-0.016478673,0.040600453,-0.02800638,0.06633598,-0.047079153,-0.008968846,-0.004289243,-0.027616,-0.03401705,0.018262355,-0.039379843,-0.0010243132,0.028597116,-0.013559064,0.046763536,-0.035549603,0.012491628,0.057109587,-0.019481635,0.03637762,-0.0013433521,0.02495684,-0.010243821,-0.04219813,-0.018158138,-0.00240093,0.026079364,-0.039592654,0.02610411,-0.019069366,-0.015094783,0.029788677,0.025238069,-0.016601754,-0.020175802,0.018825982,-0.04334887,-0.04468534,0.043603357,-0.0033776904,-0.04079708,0.0048102187,-0.024524791,-0.014824555,-0.03682036,0.019028045,-0.037638705,0.006791958,-0.04118108,0.030646976,-0.035890672,0.024403047,0.020449385,0.021247236,0.004523718,-0.04668263,-0.007420403,-0.027094536,0.04154577,0.016465219,0.010456721,-0.034846548,0.024469169,0.0028019976,-0.00022357199,-0.025103493,-0.02761501,0.029042544,0.0071963486,0.015089827,-0.010722988,0.007136887,-0.0017224804,0.0066398033,0.018007593,0.01975419,0.07704975,0.022153106,0.018037522,-0.019547502,-0.00055435207,-0.016852863,0.017602792,0.026472554,-0.009412934,0.023698727,0.04285482,0.0059047937,-0.024469176,0.009620148,-0.0012279808,-0.020169038,-0.015051825,0.01203085,-0.028063694,0.0027511925,-0.015359679,-0.036807936,-0.0020768591,-0.018455677,-0.022421718,-0.026709026,-0.058562316,0.06428957,-0.0035667515,-0.015360578,-0.00015110362,-0.016323017,0.011145623,-0.0045227194,0.016928824,-0.01058783,-0.060405955,0.06569406,0.029568514,0.030938575,0.033383925,0.041239835,0.024143599,0.010576718,-0.013025007,-0.0049419664,0.0521499,-0.021517461,-0.027968038,0.01857399,0.05367668,-0.0054875854,0.0313483,0.008693505,-0.015193749,-0.021178864,-0.006153561,0.0077875466,0.024060676,0.063377425,0.021253457,-0.042083997,0.028067244,-0.006581842,0.0071282843,-0.006422415,-0.011857471,-0.0009655672,0.03527152,-0.030571697,0.005827825,0.010611555,0.015600507,0.013236288,0.0031562955,0.034590412,-0.043591302,-0.0008179763,-0.027551409,-0.03804172,-0.00086482783,0.03381651,-0.033207797,-0.028635625,-0.0064536445,0.046969797,0.06553983,-0.002484297,0.027436456,-0.029201735,0.044342853,-0.01009429,-0.024602279,-0.005824333,0.0017688844,-0.06540628,0.0615073,0.031224923,-0.032206792,0.0009944127,-0.029774616,-0.031957854,-0.021457234,0.058586232,-0.028338231,-0.049910847,0.025937187,0.013952294,0.051359378,-0.027472898,-0.014279339,0.06785546,-0.028387275,-0.037679233,0.088731416,-0.018400233,-0.020814326,0.008780958,-0.0006407983,0.053896215,0.033188496,-0.0213407,-0.012505731,-0.026061693,-0.020274207,0.008959089,-0.056016166,-0.009784196,-0.0023167538,-0.015740888,0.032675672,-0.024266345,0.008245083,-0.0037593173,-0.0034470102,-0.016408816,-0.0119763445,-0.01583968,-0.04083876,0.011327362,0.024656525,-0.031444017,-0.028468162,-0.0121886255,-0.008610542,0.03153487,-0.07212986,-0.017107839,0.01110821,-0.017067075,-0.022098046,-0.00344999,-0.016843185,0.0001594262,-0.033865865,0.0050116074,-0.011384718,0.04597542,-0.006469601,0.011311583,0.016342504,-0.05706643,-0.031137295,0.0020527346,0.015044461,0.047488496,0.041886903,-0.01542759,0.036535576,-0.0093597155,0.006305445,0.07989142,0.0205303,-0.020440483,-0.061047185,0.005282968,-0.031146193,-0.0070730313,-0.008211226,-0.035151344,0.0038560398,-0.042658813,-0.0006306419,0.008346769,0.030108796,-0.00091333647,-0.005556151,0.0007270901,-0.075308144,0.051769357,-0.032117747,-0.016420322,-0.021393938,-0.045561843,0.015024149,-0.022735044,-0.060727593,0.05937898,-0.0017657287,-0.02604957,0.04365591,0.01776148,0.0027780528,-0.018193254,0.0081448,-0.031469222,-0.010690289,0.020206641,-0.022499785,0.020813327,0.004790662,0.019115854,-0.014165606,0.034254566,-0.017417893,0.0019417743,0.02705499,-0.01805344,-0.01917884,0.005318323,0.011842088,-0.014896111,0.0025286237,-0.0022524514,0.00027330502,-0.011292497,-0.03281068,0.037937235,-0.00409505,0.019043457,-0.02023277,0.017304964,0.005881166,0.019211194,-0.083770454,-0.030487094,-0.01425595,0.044012047,-0.0139489025,0.054518,-0.00835086,-0.018884052,0.0072624977,0.006680996,0.02193308,-0.037691083,0.017032936,-0.036794912,0.00413439,0.014216463,-0.0028291333,-0.011636572,-0.011014423,-0.0011644249,-0.012746444,-0.0072509213,0.0020021826,0.0339286,-0.008306925,0.023573149,-0.0005951755,0.050104167,0.0118867,0.013416536,-0.006694687,0.046287306,-0.033622183,0.013240143,-0.05272635,0.017669633,0.044133995,0.008915111,0.0021532925,-0.033527486,0.010352921,-0.0000625315,-0.0451437,0.028909327,0.008358023,0.011328159,0.015561081,0.06615184,0.024521237,-0.01548931,-0.038384657,-0.024037788,0.004713898,-0.035361666,-0.0024236115,-0.02471778,-0.030164076,0.0011265072,0.008452374,0.009774097,0.0067028627,0.038428735,0.0041319644,-0.007328423,0.032230742,-0.03336102,-0.011358553,0.039069045,-0.00408988,0.013824746,-0.02694883,-0.01820519,0.00048106886,0.047123738,-0.026349626,-0.010275675,0.0038645333,0.0024333987,0.02529114,-0.05023416,0.033989277,0.010437127,-0.010594778,-0.1814254,0.008874765,-0.048744984,-0.02429632,-0.05235388,-0.011636057,-0.014532614,-0.017496083,0.03897586,-0.04769643,-0.02895554,-0.014006955,-0.008152625,-0.0022625914,0.056299653,0.030646596,-0.0042774817,0.026904693,-0.019535717,0.07919335,0.004465818,-0.0007850768,-0.0030923355,0.011281966,-0.060554188,-0.015149353,0.034115653,-0.012545768,-0.06019704,0.015777742,0.03298226,-0.0128924595,0.04516177,0.026267743,-0.012876161,-0.017857872,-0.000451209,-0.04640008,0.0021797654,-0.022215987,-0.011028928,0.02983146,-0.01790041,0.02229678,0.030444836,0.05086368,-0.0007597152,-0.012791527,-0.041675646,0.0049788603,0.0135076875,-0.010058069,-0.011576785,0.017414136,-0.022469312,-0.002221888,-0.025237717,-0.017212491,0.0015337942,0.034263365,-0.03060165,0.020423504,-0.04611601,-0.056855183,-0.047773834,0.013040773,-0.0128504075,0.018158348,0.0064661647,0.02630617,-0.023808531,-0.020669084,0.030026024,-0.051853966,-0.005487125,-0.027490627,-0.016903535,-0.017998505,-0.0013828529,-0.03818782,-0.047875576,-0.030840302,-0.056570966,-0.009811687,0.048634745,0.053943735,-0.018794142,-0.016591813,-0.065253526,-0.029490007,-0.045973483,-0.01509265,0.007013323,0.033098783,-0.046038035,0.032598034,-0.007738957,-0.023206474,-0.01674569,-0.018691124,-0.04713861,-0.016627565,-0.010109872,0.021056568,-0.022169283,0.054165337,-0.014068263,0.01763968,0.04719043,-0.019452743,-0.04710953,0.013527759,-0.015000444,0.015616658,-0.095121995,0.003985372,0.0033478085,0.02987544,0.0052278857,0.009547133,0.023418814,-0.0030240056,0.0779822,-0.037693854,0.0073218266,-0.004878764,0.04054095,0.03717339,0.0057688328,0.011703725,0.031556856,-0.017517133,0.030679546,0.01640169,0.005662433,0.015817722,-0.027635133,0.021554846,-0.023545813,-0.009477885,0.020508686,-0.03642959,-0.01766828,-0.008973998,-0.030852018,0.006647848,-0.057985466,0.027324269,-0.032876685,-0.017954974,0.010354277,-0.0016796399,0.007953915,0.039628375,-0.002722565,0.02252227,-0.0004522458,0.0063981144,0.008006769,0.05361987,0.001947251,0.012105975,-0.024742981,-0.023761926,-0.012012054,0.034436148,0.0034195143,-0.037623838,-0.02239374,0.00799595,0.03363759,0.01054853,-0.031408135,-0.010339871,0.016860472,-0.0033510511,-0.0027596855,0.01815278,0.040847614,0.0019134071,0.036282293,0.0058729714,0.065959856,0.014092439,0.026879886,0.036986116,-0.028708484,0.00019183785,-0.01347916,-0.042226672,0.023879005,-0.0049921256,-0.017817132,0.010510541,0.04334863,0.060505435,0.0072268914,0.009142729,-0.0075292177,0.03157087,0.005709965,0.008496544,-0.020089092,-0.0073793605,-0.07321447,-0.005125763,0.010884455,-0.0147636905,-0.050938692,0.0248333,-0.0160438,-0.0070887916,-0.0054436903,0.039799847,0.0069172303,-0.0067506568,0.018637722,0.023855485,0.0012480823,0.007929671,-0.019375801,0.008357513,-0.012966763,0.0020459772,-0.018312274,0.001222857,-0.018580608,-0.006531202,-0.012359973,0.033083294,-0.014693151,0.014788057,-0.019249013,0.04451858,0.01902847,-0.008574831,0.04877634,0.022502221,-0.006348425,-0.030601025,0.035215423,0.00802607,-0.0042606033,0.039728794]],"total_duration":3333762993,"load_duration":3143265795,"prompt_eval_count":13}

When i send :

curl http://10.2.142.77:11434/api/embed -d '{
"model": "bge-m3:latest",
"input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such."
}'

it's fail:

POST /api/embed HTTP/1.1
Host: 10.2.142.77:11434
User-Agent: curl/7.81.0
Accept: */*
Content-Length: 175
Content-Type: application/x-www-form-urlencoded

{
  "model": "bge-m3:latest",
  "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such."
}
HTTP/1.1 500 Internal Server Error
Content-Type: application/json; charset=utf-8
Date: Thu, 15 Jan 2026 13:21:54 GMT
Content-Length: 67

{"error":"failed to encode response: json: unsupported value: NaN"}

same thing in only-cpu

<!-- gh-comment-id:3754808126 --> @nicho2 commented on GitHub (Jan 15, 2026): same thing in 0.14.0 but when i send : curl http://10.2.142.77:11434/api/embed -d '{ "model": "bge-m3:latest", "input": "This document is a draft distributed for approval." }' it's OK: POST /api/embed HTTP/1.1 Host: 10.2.142.77:11434 User-Agent: curl/7.81.0 Accept: */* Content-Length: 95 Content-Type: application/x-www-form-urlencoded { "model": "bge-m3:latest", "input": "This document is a draft distributed for approval." } HTTP/1.1 200 OK Content-Type: application/json; charset=utf-8 Date: Thu, 15 Jan 2026 13:16:49 GMT Transfer-Encoding: chunked {"model":"bge-m3:latest","embeddings":[[-0.015445454,0.003276025,-0.032736298,0.008763502,-0.0253346,-0.05621706,0.060042914,0.013629458,0.012102511,0.01625889,-0.0021870725,-0.01320955,-0.010680699,-0.00022075947,0.018077575,0.004602876,0.050414875,-0.02080775,-0.027023934,-0.002845781,-0.030523593,0.011803625,0.040470228,0.024725655,-0.047343507,0.022378556,-0.016207317,-0.001203077,0.03228503,0.02187892,0.018690186,-0.01785771,0.029428432,-0.024072818,0.0045784162,-0.044287648,-0.013129439,-0.033630155,-0.030983737,0.023344262,-0.012560762,-0.0078084823,0.021287857,-0.061550602,0.019530142,0.011605382,0.00019195586,-0.022348104,-0.025308289,-0.0028609901,-0.031649172,0.023210876,0.056044046,-0.026173636,0.02812822,0.0037022,0.021429488,-0.019578056,-0.0845583,0.023569038,-0.044206563,-0.0113979485,-0.0103847,-0.008856806,0.020307465,0.06085907,0.048012324,0.009598146,-0.024038533,-0.017801082,-0.008899206,0.032167103,-0.02682478,0.0007035052,-0.056625433,0.021817239,0.032399602,-0.07642074,0.0036620772,0.058536515,0.008637845,-0.009830092,0.01197731,0.007796856,-0.054444678,-0.0076599023,-0.047528476,0.039386824,0.019119918,-0.009168872,-0.034833595,0.015555431,0.036482897,-0.026195176,-0.03490326,0.01288963,-0.076935954,-0.004761672,0.0074276295,0.013270374,0.027959965,0.021551395,-0.009471928,-0.010893856,0.002629465,-0.019170653,0.039675627,0.011736331,0.04628006,-0.008328642,-0.011577215,0.005860599,0.033464115,-0.018660733,0.01838674,-0.007907991,-0.016121991,-0.03981626,-0.015577496,-0.0021521072,0.0028034544,0.0076389913,0.049580887,-0.029046664,0.013811698,-0.048230592,0.019610893,0.039051075,0.0260056,-0.014266633,0.04694729,0.064460024,-0.014719029,-0.023613526,-0.032929454,-0.02090901,-0.03304115,0.021721477,0.0021194443,-0.034874875,0.07790756,0.012337135,-0.045040157,-0.026725331,0.057313863,-0.1025184,0.038194004,-0.01808049,0.03202347,0.004171357,0.014145894,0.022467604,0.0084766345,-0.0104922885,0.05689718,-0.03424302,0.015268611,0.019957358,0.0132919345,0.06806766,-0.028033918,0.029516596,-0.017997397,-0.020068994,-0.0009792305,0.01766953,0.029603066,0.06188093,-0.010562154,-0.06265268,-0.000027546368,-0.0031017687,0.04113726,-0.022804378,0.01585459,0.026730621,0.047201797,-0.0032959513,0.0022920186,-0.05411061,-0.019644663,0.031293236,-0.012883818,-0.026349872,-0.008244882,-0.00010930865,0.011371867,-0.020588009,-0.012020719,-0.02025077,-0.021215668,-0.032841977,0.0034183662,0.001374491,-0.009573052,-0.025447372,-0.027364759,-0.048350755,-0.010890413,-0.068638876,-0.026589585,0.029143576,0.07048744,0.0071354685,-0.014211876,-0.026391614,-0.027603779,-0.028470699,0.017523188,-0.040969852,-0.057280704,-0.0020852506,-0.0043937746,-0.011291085,-0.011979187,0.034178134,0.028641421,0.011618161,0.010678629,-0.030960325,-0.032818086,0.007113562,0.021895787,0.058146212,0.009214191,0.005038449,-0.007188165,0.024632165,0.031550083,-0.057382002,-0.039669264,-0.0020119057,-0.019224258,-0.040861137,0.07563455,0.0095492825,-0.014664481,0.024950933,0.018580398,0.005288304,-0.012328877,0.0102612525,0.0119015025,-0.03538505,-0.04062535,0.029592982,-0.034370214,0.029243223,-0.03107611,-0.0019364593,0.023855047,-0.0009654886,-0.03617323,0.025261872,0.0060371687,0.01842621,-0.017190982,-0.0027674527,0.006770897,-0.0065281377,0.023136081,-0.03553879,0.01712718,0.03552223,0.036402587,-0.01579471,-0.033217978,0.011281189,0.030687224,-0.053479318,0.003708311,-0.026924105,0.016295,-0.015588822,0.034735266,-0.0038257819,-0.0133855445,-0.0045978953,0.036552515,-0.019900836,-0.016232884,0.048368648,0.026970956,-0.013713893,0.030491758,0.006877708,-0.008417689,-0.021315278,0.036123082,-0.011471454,-0.01975225,-0.004748489,0.058369484,-0.021009754,-0.023229802,0.01102451,-0.0082925875,-0.16528273,0.00863624,-0.004970701,-0.031583283,0.0069563654,-0.018628025,-0.035674002,-0.013911859,-0.000086524225,0.053010687,0.035070438,-0.04878839,0.018753966,0.037815135,0.01555174,0.015058085,-0.008200825,0.0029965467,-0.00072948914,0.00010433371,-0.02442157,-0.021330282,0.10416154,0.0069224103,-0.041053694,0.016387695,0.037728645,0.0024058563,-0.042805858,0.026593184,0.008263658,0.009043465,-0.0067615905,0.0076865233,-0.0040431404,0.040152516,0.05020241,-0.011230476,-0.020675005,-0.021936446,0.01432799,0.03975448,-0.016602222,0.03745323,-0.0051519643,-0.00832569,0.020547722,0.0022187612,-0.019729288,-0.009041786,-0.006680888,-0.012119521,-0.02245279,-0.011801761,-0.07318276,-0.008810027,-0.043800347,0.01201429,-0.052644923,0.055857368,-0.024241354,-0.061781283,0.021951046,-0.00045822386,-0.038456485,-0.00041926446,0.04600639,-0.011969451,0.0047146957,-0.015729569,0.023674335,-0.017260734,0.03086358,-0.022705378,0.017492127,0.023114882,0.0075497935,0.008272093,-0.031016277,-0.09495582,0.010780377,0.0034350043,-0.011891655,-0.016835637,-0.025169417,-0.017145382,-0.0024130016,0.005594143,0.08055568,0.25624886,-0.016478673,0.040600453,-0.02800638,0.06633598,-0.047079153,-0.008968846,-0.004289243,-0.027616,-0.03401705,0.018262355,-0.039379843,-0.0010243132,0.028597116,-0.013559064,0.046763536,-0.035549603,0.012491628,0.057109587,-0.019481635,0.03637762,-0.0013433521,0.02495684,-0.010243821,-0.04219813,-0.018158138,-0.00240093,0.026079364,-0.039592654,0.02610411,-0.019069366,-0.015094783,0.029788677,0.025238069,-0.016601754,-0.020175802,0.018825982,-0.04334887,-0.04468534,0.043603357,-0.0033776904,-0.04079708,0.0048102187,-0.024524791,-0.014824555,-0.03682036,0.019028045,-0.037638705,0.006791958,-0.04118108,0.030646976,-0.035890672,0.024403047,0.020449385,0.021247236,0.004523718,-0.04668263,-0.007420403,-0.027094536,0.04154577,0.016465219,0.010456721,-0.034846548,0.024469169,0.0028019976,-0.00022357199,-0.025103493,-0.02761501,0.029042544,0.0071963486,0.015089827,-0.010722988,0.007136887,-0.0017224804,0.0066398033,0.018007593,0.01975419,0.07704975,0.022153106,0.018037522,-0.019547502,-0.00055435207,-0.016852863,0.017602792,0.026472554,-0.009412934,0.023698727,0.04285482,0.0059047937,-0.024469176,0.009620148,-0.0012279808,-0.020169038,-0.015051825,0.01203085,-0.028063694,0.0027511925,-0.015359679,-0.036807936,-0.0020768591,-0.018455677,-0.022421718,-0.026709026,-0.058562316,0.06428957,-0.0035667515,-0.015360578,-0.00015110362,-0.016323017,0.011145623,-0.0045227194,0.016928824,-0.01058783,-0.060405955,0.06569406,0.029568514,0.030938575,0.033383925,0.041239835,0.024143599,0.010576718,-0.013025007,-0.0049419664,0.0521499,-0.021517461,-0.027968038,0.01857399,0.05367668,-0.0054875854,0.0313483,0.008693505,-0.015193749,-0.021178864,-0.006153561,0.0077875466,0.024060676,0.063377425,0.021253457,-0.042083997,0.028067244,-0.006581842,0.0071282843,-0.006422415,-0.011857471,-0.0009655672,0.03527152,-0.030571697,0.005827825,0.010611555,0.015600507,0.013236288,0.0031562955,0.034590412,-0.043591302,-0.0008179763,-0.027551409,-0.03804172,-0.00086482783,0.03381651,-0.033207797,-0.028635625,-0.0064536445,0.046969797,0.06553983,-0.002484297,0.027436456,-0.029201735,0.044342853,-0.01009429,-0.024602279,-0.005824333,0.0017688844,-0.06540628,0.0615073,0.031224923,-0.032206792,0.0009944127,-0.029774616,-0.031957854,-0.021457234,0.058586232,-0.028338231,-0.049910847,0.025937187,0.013952294,0.051359378,-0.027472898,-0.014279339,0.06785546,-0.028387275,-0.037679233,0.088731416,-0.018400233,-0.020814326,0.008780958,-0.0006407983,0.053896215,0.033188496,-0.0213407,-0.012505731,-0.026061693,-0.020274207,0.008959089,-0.056016166,-0.009784196,-0.0023167538,-0.015740888,0.032675672,-0.024266345,0.008245083,-0.0037593173,-0.0034470102,-0.016408816,-0.0119763445,-0.01583968,-0.04083876,0.011327362,0.024656525,-0.031444017,-0.028468162,-0.0121886255,-0.008610542,0.03153487,-0.07212986,-0.017107839,0.01110821,-0.017067075,-0.022098046,-0.00344999,-0.016843185,0.0001594262,-0.033865865,0.0050116074,-0.011384718,0.04597542,-0.006469601,0.011311583,0.016342504,-0.05706643,-0.031137295,0.0020527346,0.015044461,0.047488496,0.041886903,-0.01542759,0.036535576,-0.0093597155,0.006305445,0.07989142,0.0205303,-0.020440483,-0.061047185,0.005282968,-0.031146193,-0.0070730313,-0.008211226,-0.035151344,0.0038560398,-0.042658813,-0.0006306419,0.008346769,0.030108796,-0.00091333647,-0.005556151,0.0007270901,-0.075308144,0.051769357,-0.032117747,-0.016420322,-0.021393938,-0.045561843,0.015024149,-0.022735044,-0.060727593,0.05937898,-0.0017657287,-0.02604957,0.04365591,0.01776148,0.0027780528,-0.018193254,0.0081448,-0.031469222,-0.010690289,0.020206641,-0.022499785,0.020813327,0.004790662,0.019115854,-0.014165606,0.034254566,-0.017417893,0.0019417743,0.02705499,-0.01805344,-0.01917884,0.005318323,0.011842088,-0.014896111,0.0025286237,-0.0022524514,0.00027330502,-0.011292497,-0.03281068,0.037937235,-0.00409505,0.019043457,-0.02023277,0.017304964,0.005881166,0.019211194,-0.083770454,-0.030487094,-0.01425595,0.044012047,-0.0139489025,0.054518,-0.00835086,-0.018884052,0.0072624977,0.006680996,0.02193308,-0.037691083,0.017032936,-0.036794912,0.00413439,0.014216463,-0.0028291333,-0.011636572,-0.011014423,-0.0011644249,-0.012746444,-0.0072509213,0.0020021826,0.0339286,-0.008306925,0.023573149,-0.0005951755,0.050104167,0.0118867,0.013416536,-0.006694687,0.046287306,-0.033622183,0.013240143,-0.05272635,0.017669633,0.044133995,0.008915111,0.0021532925,-0.033527486,0.010352921,-0.0000625315,-0.0451437,0.028909327,0.008358023,0.011328159,0.015561081,0.06615184,0.024521237,-0.01548931,-0.038384657,-0.024037788,0.004713898,-0.035361666,-0.0024236115,-0.02471778,-0.030164076,0.0011265072,0.008452374,0.009774097,0.0067028627,0.038428735,0.0041319644,-0.007328423,0.032230742,-0.03336102,-0.011358553,0.039069045,-0.00408988,0.013824746,-0.02694883,-0.01820519,0.00048106886,0.047123738,-0.026349626,-0.010275675,0.0038645333,0.0024333987,0.02529114,-0.05023416,0.033989277,0.010437127,-0.010594778,-0.1814254,0.008874765,-0.048744984,-0.02429632,-0.05235388,-0.011636057,-0.014532614,-0.017496083,0.03897586,-0.04769643,-0.02895554,-0.014006955,-0.008152625,-0.0022625914,0.056299653,0.030646596,-0.0042774817,0.026904693,-0.019535717,0.07919335,0.004465818,-0.0007850768,-0.0030923355,0.011281966,-0.060554188,-0.015149353,0.034115653,-0.012545768,-0.06019704,0.015777742,0.03298226,-0.0128924595,0.04516177,0.026267743,-0.012876161,-0.017857872,-0.000451209,-0.04640008,0.0021797654,-0.022215987,-0.011028928,0.02983146,-0.01790041,0.02229678,0.030444836,0.05086368,-0.0007597152,-0.012791527,-0.041675646,0.0049788603,0.0135076875,-0.010058069,-0.011576785,0.017414136,-0.022469312,-0.002221888,-0.025237717,-0.017212491,0.0015337942,0.034263365,-0.03060165,0.020423504,-0.04611601,-0.056855183,-0.047773834,0.013040773,-0.0128504075,0.018158348,0.0064661647,0.02630617,-0.023808531,-0.020669084,0.030026024,-0.051853966,-0.005487125,-0.027490627,-0.016903535,-0.017998505,-0.0013828529,-0.03818782,-0.047875576,-0.030840302,-0.056570966,-0.009811687,0.048634745,0.053943735,-0.018794142,-0.016591813,-0.065253526,-0.029490007,-0.045973483,-0.01509265,0.007013323,0.033098783,-0.046038035,0.032598034,-0.007738957,-0.023206474,-0.01674569,-0.018691124,-0.04713861,-0.016627565,-0.010109872,0.021056568,-0.022169283,0.054165337,-0.014068263,0.01763968,0.04719043,-0.019452743,-0.04710953,0.013527759,-0.015000444,0.015616658,-0.095121995,0.003985372,0.0033478085,0.02987544,0.0052278857,0.009547133,0.023418814,-0.0030240056,0.0779822,-0.037693854,0.0073218266,-0.004878764,0.04054095,0.03717339,0.0057688328,0.011703725,0.031556856,-0.017517133,0.030679546,0.01640169,0.005662433,0.015817722,-0.027635133,0.021554846,-0.023545813,-0.009477885,0.020508686,-0.03642959,-0.01766828,-0.008973998,-0.030852018,0.006647848,-0.057985466,0.027324269,-0.032876685,-0.017954974,0.010354277,-0.0016796399,0.007953915,0.039628375,-0.002722565,0.02252227,-0.0004522458,0.0063981144,0.008006769,0.05361987,0.001947251,0.012105975,-0.024742981,-0.023761926,-0.012012054,0.034436148,0.0034195143,-0.037623838,-0.02239374,0.00799595,0.03363759,0.01054853,-0.031408135,-0.010339871,0.016860472,-0.0033510511,-0.0027596855,0.01815278,0.040847614,0.0019134071,0.036282293,0.0058729714,0.065959856,0.014092439,0.026879886,0.036986116,-0.028708484,0.00019183785,-0.01347916,-0.042226672,0.023879005,-0.0049921256,-0.017817132,0.010510541,0.04334863,0.060505435,0.0072268914,0.009142729,-0.0075292177,0.03157087,0.005709965,0.008496544,-0.020089092,-0.0073793605,-0.07321447,-0.005125763,0.010884455,-0.0147636905,-0.050938692,0.0248333,-0.0160438,-0.0070887916,-0.0054436903,0.039799847,0.0069172303,-0.0067506568,0.018637722,0.023855485,0.0012480823,0.007929671,-0.019375801,0.008357513,-0.012966763,0.0020459772,-0.018312274,0.001222857,-0.018580608,-0.006531202,-0.012359973,0.033083294,-0.014693151,0.014788057,-0.019249013,0.04451858,0.01902847,-0.008574831,0.04877634,0.022502221,-0.006348425,-0.030601025,0.035215423,0.00802607,-0.0042606033,0.039728794]],"total_duration":3333762993,"load_duration":3143265795,"prompt_eval_count":13} When i send : curl http://10.2.142.77:11434/api/embed -d '{ "model": "bge-m3:latest", "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such." }' it's fail: POST /api/embed HTTP/1.1 Host: 10.2.142.77:11434 User-Agent: curl/7.81.0 Accept: */* Content-Length: 175 Content-Type: application/x-www-form-urlencoded { "model": "bge-m3:latest", "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such." } HTTP/1.1 500 Internal Server Error Content-Type: application/json; charset=utf-8 Date: Thu, 15 Jan 2026 13:21:54 GMT Content-Length: 67 {"error":"failed to encode response: json: unsupported value: NaN"} same thing in only-cpu

GiteaMirror commented 2026-04-22 12:56:03 -05:00

Author

Owner

Copy Link

@shihkauskas commented on GitHub (Mar 2, 2026):

same thing in 0.14.0

but

when i send : curl http://10.2.142.77:11434/api/embed -d '{ "model": "bge-m3:latest", "input": "This document is a draft distributed for approval." }' it's OK:

POST /api/embed HTTP/1.1
Host: 10.2.142.77:11434
User-Agent: curl/7.81.0
Accept: */*
Content-Length: 95
Content-Type: application/x-www-form-urlencoded

{
  "model": "bge-m3:latest",
  "input": "This document is a draft distributed for approval."
}
HTTP/1.1 200 OK
Content-Type: application/json; charset=utf-8
Date: Thu, 15 Jan 2026 13:16:49 GMT
Transfer-Encoding: chunked

{"model":"bge-m3:latest","embeddings":[[-0.015445454,0.003276025,-0.032736298,0.008763502,-0.0253346,-0.05621706,0.060042914,0.013629458,0.012102511,0.01625889,-0.0021870725,-0.01320955,-0.010680699,-0.00022075947,0.018077575,0.004602876,0.050414875,-0.02080775,-0.027023934,-0.002845781,-0.030523593,0.011803625,0.040470228,0.024725655,-0.047343507,0.022378556,-0.016207317,-0.001203077,0.03228503,0.02187892,0.018690186,-0.01785771,0.029428432,-0.024072818,0.0045784162,-0.044287648,-0.013129439,-0.033630155,-0.030983737,0.023344262,-0.012560762,-0.0078084823,0.021287857,-0.061550602,0.019530142,0.011605382,0.00019195586,-0.022348104,-0.025308289,-0.0028609901,-0.031649172,0.023210876,0.056044046,-0.026173636,0.02812822,0.0037022,0.021429488,-0.019578056,-0.0845583,0.023569038,-0.044206563,-0.0113979485,-0.0103847,-0.008856806,0.020307465,0.06085907,0.048012324,0.009598146,-0.024038533,-0.017801082,-0.008899206,0.032167103,-0.02682478,0.0007035052,-0.056625433,0.021817239,0.032399602,-0.07642074,0.0036620772,0.058536515,0.008637845,-0.009830092,0.01197731,0.007796856,-0.054444678,-0.0076599023,-0.047528476,0.039386824,0.019119918,-0.009168872,-0.034833595,0.015555431,0.036482897,-0.026195176,-0.03490326,0.01288963,-0.076935954,-0.004761672,0.0074276295,0.013270374,0.027959965,0.021551395,-0.009471928,-0.010893856,0.002629465,-0.019170653,0.039675627,0.011736331,0.04628006,-0.008328642,-0.011577215,0.005860599,0.033464115,-0.018660733,0.01838674,-0.007907991,-0.016121991,-0.03981626,-0.015577496,-0.0021521072,0.0028034544,0.0076389913,0.049580887,-0.029046664,0.013811698,-0.048230592,0.019610893,0.039051075,0.0260056,-0.014266633,0.04694729,0.064460024,-0.014719029,-0.023613526,-0.032929454,-0.02090901,-0.03304115,0.021721477,0.0021194443,-0.034874875,0.07790756,0.012337135,-0.045040157,-0.026725331,0.057313863,-0.1025184,0.038194004,-0.01808049,0.03202347,0.004171357,0.014145894,0.022467604,0.0084766345,-0.0104922885,0.05689718,-0.03424302,0.015268611,0.019957358,0.0132919345,0.06806766,-0.028033918,0.029516596,-0.017997397,-0.020068994,-0.0009792305,0.01766953,0.029603066,0.06188093,-0.010562154,-0.06265268,-0.000027546368,-0.0031017687,0.04113726,-0.022804378,0.01585459,0.026730621,0.047201797,-0.0032959513,0.0022920186,-0.05411061,-0.019644663,0.031293236,-0.012883818,-0.026349872,-0.008244882,-0.00010930865,0.011371867,-0.020588009,-0.012020719,-0.02025077,-0.021215668,-0.032841977,0.0034183662,0.001374491,-0.009573052,-0.025447372,-0.027364759,-0.048350755,-0.010890413,-0.068638876,-0.026589585,0.029143576,0.07048744,0.0071354685,-0.014211876,-0.026391614,-0.027603779,-0.028470699,0.017523188,-0.040969852,-0.057280704,-0.0020852506,-0.0043937746,-0.011291085,-0.011979187,0.034178134,0.028641421,0.011618161,0.010678629,-0.030960325,-0.032818086,0.007113562,0.021895787,0.058146212,0.009214191,0.005038449,-0.007188165,0.024632165,0.031550083,-0.057382002,-0.039669264,-0.0020119057,-0.019224258,-0.040861137,0.07563455,0.0095492825,-0.014664481,0.024950933,0.018580398,0.005288304,-0.012328877,0.0102612525,0.0119015025,-0.03538505,-0.04062535,0.029592982,-0.034370214,0.029243223,-0.03107611,-0.0019364593,0.023855047,-0.0009654886,-0.03617323,0.025261872,0.0060371687,0.01842621,-0.017190982,-0.0027674527,0.006770897,-0.0065281377,0.023136081,-0.03553879,0.01712718,0.03552223,0.036402587,-0.01579471,-0.033217978,0.011281189,0.030687224,-0.053479318,0.003708311,-0.026924105,0.016295,-0.015588822,0.034735266,-0.0038257819,-0.0133855445,-0.0045978953,0.036552515,-0.019900836,-0.016232884,0.048368648,0.026970956,-0.013713893,0.030491758,0.006877708,-0.008417689,-0.021315278,0.036123082,-0.011471454,-0.01975225,-0.004748489,0.058369484,-0.021009754,-0.023229802,0.01102451,-0.0082925875,-0.16528273,0.00863624,-0.004970701,-0.031583283,0.0069563654,-0.018628025,-0.035674002,-0.013911859,-0.000086524225,0.053010687,0.035070438,-0.04878839,0.018753966,0.037815135,0.01555174,0.015058085,-0.008200825,0.0029965467,-0.00072948914,0.00010433371,-0.02442157,-0.021330282,0.10416154,0.0069224103,-0.041053694,0.016387695,0.037728645,0.0024058563,-0.042805858,0.026593184,0.008263658,0.009043465,-0.0067615905,0.0076865233,-0.0040431404,0.040152516,0.05020241,-0.011230476,-0.020675005,-0.021936446,0.01432799,0.03975448,-0.016602222,0.03745323,-0.0051519643,-0.00832569,0.020547722,0.0022187612,-0.019729288,-0.009041786,-0.006680888,-0.012119521,-0.02245279,-0.011801761,-0.07318276,-0.008810027,-0.043800347,0.01201429,-0.052644923,0.055857368,-0.024241354,-0.061781283,0.021951046,-0.00045822386,-0.038456485,-0.00041926446,0.04600639,-0.011969451,0.0047146957,-0.015729569,0.023674335,-0.017260734,0.03086358,-0.022705378,0.017492127,0.023114882,0.0075497935,0.008272093,-0.031016277,-0.09495582,0.010780377,0.0034350043,-0.011891655,-0.016835637,-0.025169417,-0.017145382,-0.0024130016,0.005594143,0.08055568,0.25624886,-0.016478673,0.040600453,-0.02800638,0.06633598,-0.047079153,-0.008968846,-0.004289243,-0.027616,-0.03401705,0.018262355,-0.039379843,-0.0010243132,0.028597116,-0.013559064,0.046763536,-0.035549603,0.012491628,0.057109587,-0.019481635,0.03637762,-0.0013433521,0.02495684,-0.010243821,-0.04219813,-0.018158138,-0.00240093,0.026079364,-0.039592654,0.02610411,-0.019069366,-0.015094783,0.029788677,0.025238069,-0.016601754,-0.020175802,0.018825982,-0.04334887,-0.04468534,0.043603357,-0.0033776904,-0.04079708,0.0048102187,-0.024524791,-0.014824555,-0.03682036,0.019028045,-0.037638705,0.006791958,-0.04118108,0.030646976,-0.035890672,0.024403047,0.020449385,0.021247236,0.004523718,-0.04668263,-0.007420403,-0.027094536,0.04154577,0.016465219,0.010456721,-0.034846548,0.024469169,0.0028019976,-0.00022357199,-0.025103493,-0.02761501,0.029042544,0.0071963486,0.015089827,-0.010722988,0.007136887,-0.0017224804,0.0066398033,0.018007593,0.01975419,0.07704975,0.022153106,0.018037522,-0.019547502,-0.00055435207,-0.016852863,0.017602792,0.026472554,-0.009412934,0.023698727,0.04285482,0.0059047937,-0.024469176,0.009620148,-0.0012279808,-0.020169038,-0.015051825,0.01203085,-0.028063694,0.0027511925,-0.015359679,-0.036807936,-0.0020768591,-0.018455677,-0.022421718,-0.026709026,-0.058562316,0.06428957,-0.0035667515,-0.015360578,-0.00015110362,-0.016323017,0.011145623,-0.0045227194,0.016928824,-0.01058783,-0.060405955,0.06569406,0.029568514,0.030938575,0.033383925,0.041239835,0.024143599,0.010576718,-0.013025007,-0.0049419664,0.0521499,-0.021517461,-0.027968038,0.01857399,0.05367668,-0.0054875854,0.0313483,0.008693505,-0.015193749,-0.021178864,-0.006153561,0.0077875466,0.024060676,0.063377425,0.021253457,-0.042083997,0.028067244,-0.006581842,0.0071282843,-0.006422415,-0.011857471,-0.0009655672,0.03527152,-0.030571697,0.005827825,0.010611555,0.015600507,0.013236288,0.0031562955,0.034590412,-0.043591302,-0.0008179763,-0.027551409,-0.03804172,-0.00086482783,0.03381651,-0.033207797,-0.028635625,-0.0064536445,0.046969797,0.06553983,-0.002484297,0.027436456,-0.029201735,0.044342853,-0.01009429,-0.024602279,-0.005824333,0.0017688844,-0.06540628,0.0615073,0.031224923,-0.032206792,0.0009944127,-0.029774616,-0.031957854,-0.021457234,0.058586232,-0.028338231,-0.049910847,0.025937187,0.013952294,0.051359378,-0.027472898,-0.014279339,0.06785546,-0.028387275,-0.037679233,0.088731416,-0.018400233,-0.020814326,0.008780958,-0.0006407983,0.053896215,0.033188496,-0.0213407,-0.012505731,-0.026061693,-0.020274207,0.008959089,-0.056016166,-0.009784196,-0.0023167538,-0.015740888,0.032675672,-0.024266345,0.008245083,-0.0037593173,-0.0034470102,-0.016408816,-0.0119763445,-0.01583968,-0.04083876,0.011327362,0.024656525,-0.031444017,-0.028468162,-0.0121886255,-0.008610542,0.03153487,-0.07212986,-0.017107839,0.01110821,-0.017067075,-0.022098046,-0.00344999,-0.016843185,0.0001594262,-0.033865865,0.0050116074,-0.011384718,0.04597542,-0.006469601,0.011311583,0.016342504,-0.05706643,-0.031137295,0.0020527346,0.015044461,0.047488496,0.041886903,-0.01542759,0.036535576,-0.0093597155,0.006305445,0.07989142,0.0205303,-0.020440483,-0.061047185,0.005282968,-0.031146193,-0.0070730313,-0.008211226,-0.035151344,0.0038560398,-0.042658813,-0.0006306419,0.008346769,0.030108796,-0.00091333647,-0.005556151,0.0007270901,-0.075308144,0.051769357,-0.032117747,-0.016420322,-0.021393938,-0.045561843,0.015024149,-0.022735044,-0.060727593,0.05937898,-0.0017657287,-0.02604957,0.04365591,0.01776148,0.0027780528,-0.018193254,0.0081448,-0.031469222,-0.010690289,0.020206641,-0.022499785,0.020813327,0.004790662,0.019115854,-0.014165606,0.034254566,-0.017417893,0.0019417743,0.02705499,-0.01805344,-0.01917884,0.005318323,0.011842088,-0.014896111,0.0025286237,-0.0022524514,0.00027330502,-0.011292497,-0.03281068,0.037937235,-0.00409505,0.019043457,-0.02023277,0.017304964,0.005881166,0.019211194,-0.083770454,-0.030487094,-0.01425595,0.044012047,-0.0139489025,0.054518,-0.00835086,-0.018884052,0.0072624977,0.006680996,0.02193308,-0.037691083,0.017032936,-0.036794912,0.00413439,0.014216463,-0.0028291333,-0.011636572,-0.011014423,-0.0011644249,-0.012746444,-0.0072509213,0.0020021826,0.0339286,-0.008306925,0.023573149,-0.0005951755,0.050104167,0.0118867,0.013416536,-0.006694687,0.046287306,-0.033622183,0.013240143,-0.05272635,0.017669633,0.044133995,0.008915111,0.0021532925,-0.033527486,0.010352921,-0.0000625315,-0.0451437,0.028909327,0.008358023,0.011328159,0.015561081,0.06615184,0.024521237,-0.01548931,-0.038384657,-0.024037788,0.004713898,-0.035361666,-0.0024236115,-0.02471778,-0.030164076,0.0011265072,0.008452374,0.009774097,0.0067028627,0.038428735,0.0041319644,-0.007328423,0.032230742,-0.03336102,-0.011358553,0.039069045,-0.00408988,0.013824746,-0.02694883,-0.01820519,0.00048106886,0.047123738,-0.026349626,-0.010275675,0.0038645333,0.0024333987,0.02529114,-0.05023416,0.033989277,0.010437127,-0.010594778,-0.1814254,0.008874765,-0.048744984,-0.02429632,-0.05235388,-0.011636057,-0.014532614,-0.017496083,0.03897586,-0.04769643,-0.02895554,-0.014006955,-0.008152625,-0.0022625914,0.056299653,0.030646596,-0.0042774817,0.026904693,-0.019535717,0.07919335,0.004465818,-0.0007850768,-0.0030923355,0.011281966,-0.060554188,-0.015149353,0.034115653,-0.012545768,-0.06019704,0.015777742,0.03298226,-0.0128924595,0.04516177,0.026267743,-0.012876161,-0.017857872,-0.000451209,-0.04640008,0.0021797654,-0.022215987,-0.011028928,0.02983146,-0.01790041,0.02229678,0.030444836,0.05086368,-0.0007597152,-0.012791527,-0.041675646,0.0049788603,0.0135076875,-0.010058069,-0.011576785,0.017414136,-0.022469312,-0.002221888,-0.025237717,-0.017212491,0.0015337942,0.034263365,-0.03060165,0.020423504,-0.04611601,-0.056855183,-0.047773834,0.013040773,-0.0128504075,0.018158348,0.0064661647,0.02630617,-0.023808531,-0.020669084,0.030026024,-0.051853966,-0.005487125,-0.027490627,-0.016903535,-0.017998505,-0.0013828529,-0.03818782,-0.047875576,-0.030840302,-0.056570966,-0.009811687,0.048634745,0.053943735,-0.018794142,-0.016591813,-0.065253526,-0.029490007,-0.045973483,-0.01509265,0.007013323,0.033098783,-0.046038035,0.032598034,-0.007738957,-0.023206474,-0.01674569,-0.018691124,-0.04713861,-0.016627565,-0.010109872,0.021056568,-0.022169283,0.054165337,-0.014068263,0.01763968,0.04719043,-0.019452743,-0.04710953,0.013527759,-0.015000444,0.015616658,-0.095121995,0.003985372,0.0033478085,0.02987544,0.0052278857,0.009547133,0.023418814,-0.0030240056,0.0779822,-0.037693854,0.0073218266,-0.004878764,0.04054095,0.03717339,0.0057688328,0.011703725,0.031556856,-0.017517133,0.030679546,0.01640169,0.005662433,0.015817722,-0.027635133,0.021554846,-0.023545813,-0.009477885,0.020508686,-0.03642959,-0.01766828,-0.008973998,-0.030852018,0.006647848,-0.057985466,0.027324269,-0.032876685,-0.017954974,0.010354277,-0.0016796399,0.007953915,0.039628375,-0.002722565,0.02252227,-0.0004522458,0.0063981144,0.008006769,0.05361987,0.001947251,0.012105975,-0.024742981,-0.023761926,-0.012012054,0.034436148,0.0034195143,-0.037623838,-0.02239374,0.00799595,0.03363759,0.01054853,-0.031408135,-0.010339871,0.016860472,-0.0033510511,-0.0027596855,0.01815278,0.040847614,0.0019134071,0.036282293,0.0058729714,0.065959856,0.014092439,0.026879886,0.036986116,-0.028708484,0.00019183785,-0.01347916,-0.042226672,0.023879005,-0.0049921256,-0.017817132,0.010510541,0.04334863,0.060505435,0.0072268914,0.009142729,-0.0075292177,0.03157087,0.005709965,0.008496544,-0.020089092,-0.0073793605,-0.07321447,-0.005125763,0.010884455,-0.0147636905,-0.050938692,0.0248333,-0.0160438,-0.0070887916,-0.0054436903,0.039799847,0.0069172303,-0.0067506568,0.018637722,0.023855485,0.0012480823,0.007929671,-0.019375801,0.008357513,-0.012966763,0.0020459772,-0.018312274,0.001222857,-0.018580608,-0.006531202,-0.012359973,0.033083294,-0.014693151,0.014788057,-0.019249013,0.04451858,0.01902847,-0.008574831,0.04877634,0.022502221,-0.006348425,-0.030601025,0.035215423,0.00802607,-0.0042606033,0.039728794]],"total_duration":3333762993,"load_duration":3143265795,"prompt_eval_count":13}

When i send :

curl http://10.2.142.77:11434/api/embed -d '{ "model": "bge-m3:latest", "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such." }'

it's fail:

POST /api/embed HTTP/1.1
Host: 10.2.142.77:11434
User-Agent: curl/7.81.0
Accept: */*
Content-Length: 175
Content-Type: application/x-www-form-urlencoded

{
  "model": "bge-m3:latest",
  "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such."
}
HTTP/1.1 500 Internal Server Error
Content-Type: application/json; charset=utf-8
Date: Thu, 15 Jan 2026 13:21:54 GMT
Content-Length: 67

{"error":"failed to encode response: json: unsupported value: NaN"}

same thing in only-cpu

the same error in version 0.17.0

<!-- gh-comment-id:3983668511 --> @shihkauskas commented on GitHub (Mar 2, 2026): > same thing in 0.14.0 > > but > > when i send : curl http://10.2.142.77:11434/api/embed -d '{ "model": "bge-m3:latest", "input": "This document is a draft distributed for approval." }' it's OK: > > ``` > POST /api/embed HTTP/1.1 > Host: 10.2.142.77:11434 > User-Agent: curl/7.81.0 > Accept: */* > Content-Length: 95 > Content-Type: application/x-www-form-urlencoded > > { > "model": "bge-m3:latest", > "input": "This document is a draft distributed for approval." > } > HTTP/1.1 200 OK > Content-Type: application/json; charset=utf-8 > Date: Thu, 15 Jan 2026 13:16:49 GMT > Transfer-Encoding: chunked > > {"model":"bge-m3:latest","embeddings":[[-0.015445454,0.003276025,-0.032736298,0.008763502,-0.0253346,-0.05621706,0.060042914,0.013629458,0.012102511,0.01625889,-0.0021870725,-0.01320955,-0.010680699,-0.00022075947,0.018077575,0.004602876,0.050414875,-0.02080775,-0.027023934,-0.002845781,-0.030523593,0.011803625,0.040470228,0.024725655,-0.047343507,0.022378556,-0.016207317,-0.001203077,0.03228503,0.02187892,0.018690186,-0.01785771,0.029428432,-0.024072818,0.0045784162,-0.044287648,-0.013129439,-0.033630155,-0.030983737,0.023344262,-0.012560762,-0.0078084823,0.021287857,-0.061550602,0.019530142,0.011605382,0.00019195586,-0.022348104,-0.025308289,-0.0028609901,-0.031649172,0.023210876,0.056044046,-0.026173636,0.02812822,0.0037022,0.021429488,-0.019578056,-0.0845583,0.023569038,-0.044206563,-0.0113979485,-0.0103847,-0.008856806,0.020307465,0.06085907,0.048012324,0.009598146,-0.024038533,-0.017801082,-0.008899206,0.032167103,-0.02682478,0.0007035052,-0.056625433,0.021817239,0.032399602,-0.07642074,0.0036620772,0.058536515,0.008637845,-0.009830092,0.01197731,0.007796856,-0.054444678,-0.0076599023,-0.047528476,0.039386824,0.019119918,-0.009168872,-0.034833595,0.015555431,0.036482897,-0.026195176,-0.03490326,0.01288963,-0.076935954,-0.004761672,0.0074276295,0.013270374,0.027959965,0.021551395,-0.009471928,-0.010893856,0.002629465,-0.019170653,0.039675627,0.011736331,0.04628006,-0.008328642,-0.011577215,0.005860599,0.033464115,-0.018660733,0.01838674,-0.007907991,-0.016121991,-0.03981626,-0.015577496,-0.0021521072,0.0028034544,0.0076389913,0.049580887,-0.029046664,0.013811698,-0.048230592,0.019610893,0.039051075,0.0260056,-0.014266633,0.04694729,0.064460024,-0.014719029,-0.023613526,-0.032929454,-0.02090901,-0.03304115,0.021721477,0.0021194443,-0.034874875,0.07790756,0.012337135,-0.045040157,-0.026725331,0.057313863,-0.1025184,0.038194004,-0.01808049,0.03202347,0.004171357,0.014145894,0.022467604,0.0084766345,-0.0104922885,0.05689718,-0.03424302,0.015268611,0.019957358,0.0132919345,0.06806766,-0.028033918,0.029516596,-0.017997397,-0.020068994,-0.0009792305,0.01766953,0.029603066,0.06188093,-0.010562154,-0.06265268,-0.000027546368,-0.0031017687,0.04113726,-0.022804378,0.01585459,0.026730621,0.047201797,-0.0032959513,0.0022920186,-0.05411061,-0.019644663,0.031293236,-0.012883818,-0.026349872,-0.008244882,-0.00010930865,0.011371867,-0.020588009,-0.012020719,-0.02025077,-0.021215668,-0.032841977,0.0034183662,0.001374491,-0.009573052,-0.025447372,-0.027364759,-0.048350755,-0.010890413,-0.068638876,-0.026589585,0.029143576,0.07048744,0.0071354685,-0.014211876,-0.026391614,-0.027603779,-0.028470699,0.017523188,-0.040969852,-0.057280704,-0.0020852506,-0.0043937746,-0.011291085,-0.011979187,0.034178134,0.028641421,0.011618161,0.010678629,-0.030960325,-0.032818086,0.007113562,0.021895787,0.058146212,0.009214191,0.005038449,-0.007188165,0.024632165,0.031550083,-0.057382002,-0.039669264,-0.0020119057,-0.019224258,-0.040861137,0.07563455,0.0095492825,-0.014664481,0.024950933,0.018580398,0.005288304,-0.012328877,0.0102612525,0.0119015025,-0.03538505,-0.04062535,0.029592982,-0.034370214,0.029243223,-0.03107611,-0.0019364593,0.023855047,-0.0009654886,-0.03617323,0.025261872,0.0060371687,0.01842621,-0.017190982,-0.0027674527,0.006770897,-0.0065281377,0.023136081,-0.03553879,0.01712718,0.03552223,0.036402587,-0.01579471,-0.033217978,0.011281189,0.030687224,-0.053479318,0.003708311,-0.026924105,0.016295,-0.015588822,0.034735266,-0.0038257819,-0.0133855445,-0.0045978953,0.036552515,-0.019900836,-0.016232884,0.048368648,0.026970956,-0.013713893,0.030491758,0.006877708,-0.008417689,-0.021315278,0.036123082,-0.011471454,-0.01975225,-0.004748489,0.058369484,-0.021009754,-0.023229802,0.01102451,-0.0082925875,-0.16528273,0.00863624,-0.004970701,-0.031583283,0.0069563654,-0.018628025,-0.035674002,-0.013911859,-0.000086524225,0.053010687,0.035070438,-0.04878839,0.018753966,0.037815135,0.01555174,0.015058085,-0.008200825,0.0029965467,-0.00072948914,0.00010433371,-0.02442157,-0.021330282,0.10416154,0.0069224103,-0.041053694,0.016387695,0.037728645,0.0024058563,-0.042805858,0.026593184,0.008263658,0.009043465,-0.0067615905,0.0076865233,-0.0040431404,0.040152516,0.05020241,-0.011230476,-0.020675005,-0.021936446,0.01432799,0.03975448,-0.016602222,0.03745323,-0.0051519643,-0.00832569,0.020547722,0.0022187612,-0.019729288,-0.009041786,-0.006680888,-0.012119521,-0.02245279,-0.011801761,-0.07318276,-0.008810027,-0.043800347,0.01201429,-0.052644923,0.055857368,-0.024241354,-0.061781283,0.021951046,-0.00045822386,-0.038456485,-0.00041926446,0.04600639,-0.011969451,0.0047146957,-0.015729569,0.023674335,-0.017260734,0.03086358,-0.022705378,0.017492127,0.023114882,0.0075497935,0.008272093,-0.031016277,-0.09495582,0.010780377,0.0034350043,-0.011891655,-0.016835637,-0.025169417,-0.017145382,-0.0024130016,0.005594143,0.08055568,0.25624886,-0.016478673,0.040600453,-0.02800638,0.06633598,-0.047079153,-0.008968846,-0.004289243,-0.027616,-0.03401705,0.018262355,-0.039379843,-0.0010243132,0.028597116,-0.013559064,0.046763536,-0.035549603,0.012491628,0.057109587,-0.019481635,0.03637762,-0.0013433521,0.02495684,-0.010243821,-0.04219813,-0.018158138,-0.00240093,0.026079364,-0.039592654,0.02610411,-0.019069366,-0.015094783,0.029788677,0.025238069,-0.016601754,-0.020175802,0.018825982,-0.04334887,-0.04468534,0.043603357,-0.0033776904,-0.04079708,0.0048102187,-0.024524791,-0.014824555,-0.03682036,0.019028045,-0.037638705,0.006791958,-0.04118108,0.030646976,-0.035890672,0.024403047,0.020449385,0.021247236,0.004523718,-0.04668263,-0.007420403,-0.027094536,0.04154577,0.016465219,0.010456721,-0.034846548,0.024469169,0.0028019976,-0.00022357199,-0.025103493,-0.02761501,0.029042544,0.0071963486,0.015089827,-0.010722988,0.007136887,-0.0017224804,0.0066398033,0.018007593,0.01975419,0.07704975,0.022153106,0.018037522,-0.019547502,-0.00055435207,-0.016852863,0.017602792,0.026472554,-0.009412934,0.023698727,0.04285482,0.0059047937,-0.024469176,0.009620148,-0.0012279808,-0.020169038,-0.015051825,0.01203085,-0.028063694,0.0027511925,-0.015359679,-0.036807936,-0.0020768591,-0.018455677,-0.022421718,-0.026709026,-0.058562316,0.06428957,-0.0035667515,-0.015360578,-0.00015110362,-0.016323017,0.011145623,-0.0045227194,0.016928824,-0.01058783,-0.060405955,0.06569406,0.029568514,0.030938575,0.033383925,0.041239835,0.024143599,0.010576718,-0.013025007,-0.0049419664,0.0521499,-0.021517461,-0.027968038,0.01857399,0.05367668,-0.0054875854,0.0313483,0.008693505,-0.015193749,-0.021178864,-0.006153561,0.0077875466,0.024060676,0.063377425,0.021253457,-0.042083997,0.028067244,-0.006581842,0.0071282843,-0.006422415,-0.011857471,-0.0009655672,0.03527152,-0.030571697,0.005827825,0.010611555,0.015600507,0.013236288,0.0031562955,0.034590412,-0.043591302,-0.0008179763,-0.027551409,-0.03804172,-0.00086482783,0.03381651,-0.033207797,-0.028635625,-0.0064536445,0.046969797,0.06553983,-0.002484297,0.027436456,-0.029201735,0.044342853,-0.01009429,-0.024602279,-0.005824333,0.0017688844,-0.06540628,0.0615073,0.031224923,-0.032206792,0.0009944127,-0.029774616,-0.031957854,-0.021457234,0.058586232,-0.028338231,-0.049910847,0.025937187,0.013952294,0.051359378,-0.027472898,-0.014279339,0.06785546,-0.028387275,-0.037679233,0.088731416,-0.018400233,-0.020814326,0.008780958,-0.0006407983,0.053896215,0.033188496,-0.0213407,-0.012505731,-0.026061693,-0.020274207,0.008959089,-0.056016166,-0.009784196,-0.0023167538,-0.015740888,0.032675672,-0.024266345,0.008245083,-0.0037593173,-0.0034470102,-0.016408816,-0.0119763445,-0.01583968,-0.04083876,0.011327362,0.024656525,-0.031444017,-0.028468162,-0.0121886255,-0.008610542,0.03153487,-0.07212986,-0.017107839,0.01110821,-0.017067075,-0.022098046,-0.00344999,-0.016843185,0.0001594262,-0.033865865,0.0050116074,-0.011384718,0.04597542,-0.006469601,0.011311583,0.016342504,-0.05706643,-0.031137295,0.0020527346,0.015044461,0.047488496,0.041886903,-0.01542759,0.036535576,-0.0093597155,0.006305445,0.07989142,0.0205303,-0.020440483,-0.061047185,0.005282968,-0.031146193,-0.0070730313,-0.008211226,-0.035151344,0.0038560398,-0.042658813,-0.0006306419,0.008346769,0.030108796,-0.00091333647,-0.005556151,0.0007270901,-0.075308144,0.051769357,-0.032117747,-0.016420322,-0.021393938,-0.045561843,0.015024149,-0.022735044,-0.060727593,0.05937898,-0.0017657287,-0.02604957,0.04365591,0.01776148,0.0027780528,-0.018193254,0.0081448,-0.031469222,-0.010690289,0.020206641,-0.022499785,0.020813327,0.004790662,0.019115854,-0.014165606,0.034254566,-0.017417893,0.0019417743,0.02705499,-0.01805344,-0.01917884,0.005318323,0.011842088,-0.014896111,0.0025286237,-0.0022524514,0.00027330502,-0.011292497,-0.03281068,0.037937235,-0.00409505,0.019043457,-0.02023277,0.017304964,0.005881166,0.019211194,-0.083770454,-0.030487094,-0.01425595,0.044012047,-0.0139489025,0.054518,-0.00835086,-0.018884052,0.0072624977,0.006680996,0.02193308,-0.037691083,0.017032936,-0.036794912,0.00413439,0.014216463,-0.0028291333,-0.011636572,-0.011014423,-0.0011644249,-0.012746444,-0.0072509213,0.0020021826,0.0339286,-0.008306925,0.023573149,-0.0005951755,0.050104167,0.0118867,0.013416536,-0.006694687,0.046287306,-0.033622183,0.013240143,-0.05272635,0.017669633,0.044133995,0.008915111,0.0021532925,-0.033527486,0.010352921,-0.0000625315,-0.0451437,0.028909327,0.008358023,0.011328159,0.015561081,0.06615184,0.024521237,-0.01548931,-0.038384657,-0.024037788,0.004713898,-0.035361666,-0.0024236115,-0.02471778,-0.030164076,0.0011265072,0.008452374,0.009774097,0.0067028627,0.038428735,0.0041319644,-0.007328423,0.032230742,-0.03336102,-0.011358553,0.039069045,-0.00408988,0.013824746,-0.02694883,-0.01820519,0.00048106886,0.047123738,-0.026349626,-0.010275675,0.0038645333,0.0024333987,0.02529114,-0.05023416,0.033989277,0.010437127,-0.010594778,-0.1814254,0.008874765,-0.048744984,-0.02429632,-0.05235388,-0.011636057,-0.014532614,-0.017496083,0.03897586,-0.04769643,-0.02895554,-0.014006955,-0.008152625,-0.0022625914,0.056299653,0.030646596,-0.0042774817,0.026904693,-0.019535717,0.07919335,0.004465818,-0.0007850768,-0.0030923355,0.011281966,-0.060554188,-0.015149353,0.034115653,-0.012545768,-0.06019704,0.015777742,0.03298226,-0.0128924595,0.04516177,0.026267743,-0.012876161,-0.017857872,-0.000451209,-0.04640008,0.0021797654,-0.022215987,-0.011028928,0.02983146,-0.01790041,0.02229678,0.030444836,0.05086368,-0.0007597152,-0.012791527,-0.041675646,0.0049788603,0.0135076875,-0.010058069,-0.011576785,0.017414136,-0.022469312,-0.002221888,-0.025237717,-0.017212491,0.0015337942,0.034263365,-0.03060165,0.020423504,-0.04611601,-0.056855183,-0.047773834,0.013040773,-0.0128504075,0.018158348,0.0064661647,0.02630617,-0.023808531,-0.020669084,0.030026024,-0.051853966,-0.005487125,-0.027490627,-0.016903535,-0.017998505,-0.0013828529,-0.03818782,-0.047875576,-0.030840302,-0.056570966,-0.009811687,0.048634745,0.053943735,-0.018794142,-0.016591813,-0.065253526,-0.029490007,-0.045973483,-0.01509265,0.007013323,0.033098783,-0.046038035,0.032598034,-0.007738957,-0.023206474,-0.01674569,-0.018691124,-0.04713861,-0.016627565,-0.010109872,0.021056568,-0.022169283,0.054165337,-0.014068263,0.01763968,0.04719043,-0.019452743,-0.04710953,0.013527759,-0.015000444,0.015616658,-0.095121995,0.003985372,0.0033478085,0.02987544,0.0052278857,0.009547133,0.023418814,-0.0030240056,0.0779822,-0.037693854,0.0073218266,-0.004878764,0.04054095,0.03717339,0.0057688328,0.011703725,0.031556856,-0.017517133,0.030679546,0.01640169,0.005662433,0.015817722,-0.027635133,0.021554846,-0.023545813,-0.009477885,0.020508686,-0.03642959,-0.01766828,-0.008973998,-0.030852018,0.006647848,-0.057985466,0.027324269,-0.032876685,-0.017954974,0.010354277,-0.0016796399,0.007953915,0.039628375,-0.002722565,0.02252227,-0.0004522458,0.0063981144,0.008006769,0.05361987,0.001947251,0.012105975,-0.024742981,-0.023761926,-0.012012054,0.034436148,0.0034195143,-0.037623838,-0.02239374,0.00799595,0.03363759,0.01054853,-0.031408135,-0.010339871,0.016860472,-0.0033510511,-0.0027596855,0.01815278,0.040847614,0.0019134071,0.036282293,0.0058729714,0.065959856,0.014092439,0.026879886,0.036986116,-0.028708484,0.00019183785,-0.01347916,-0.042226672,0.023879005,-0.0049921256,-0.017817132,0.010510541,0.04334863,0.060505435,0.0072268914,0.009142729,-0.0075292177,0.03157087,0.005709965,0.008496544,-0.020089092,-0.0073793605,-0.07321447,-0.005125763,0.010884455,-0.0147636905,-0.050938692,0.0248333,-0.0160438,-0.0070887916,-0.0054436903,0.039799847,0.0069172303,-0.0067506568,0.018637722,0.023855485,0.0012480823,0.007929671,-0.019375801,0.008357513,-0.012966763,0.0020459772,-0.018312274,0.001222857,-0.018580608,-0.006531202,-0.012359973,0.033083294,-0.014693151,0.014788057,-0.019249013,0.04451858,0.01902847,-0.008574831,0.04877634,0.022502221,-0.006348425,-0.030601025,0.035215423,0.00802607,-0.0042606033,0.039728794]],"total_duration":3333762993,"load_duration":3143265795,"prompt_eval_count":13} > ``` > > When i send : > > curl http://10.2.142.77:11434/api/embed -d '{ "model": "bge-m3:latest", "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such." }' > > it's fail: > > ``` > POST /api/embed HTTP/1.1 > Host: 10.2.142.77:11434 > User-Agent: curl/7.81.0 > Accept: */* > Content-Length: 175 > Content-Type: application/x-www-form-urlencoded > > { > "model": "bge-m3:latest", > "input": "This document is a draft distributed for approval. It may not be referred to as an International Standard until published as such." > } > HTTP/1.1 500 Internal Server Error > Content-Type: application/json; charset=utf-8 > Date: Thu, 15 Jan 2026 13:21:54 GMT > Content-Length: 67 > > {"error":"failed to encode response: json: unsupported value: NaN"} > ``` > > same thing in only-cpu the same error in version 0.17.0

GiteaMirror commented 2026-04-22 12:56:03 -05:00

Author

Owner

Copy Link

@dominicx commented on GitHub (Apr 16, 2026):

the same error in ollama 0.20.3

<!-- gh-comment-id:4258405985 --> @dominicx commented on GitHub (Apr 16, 2026): the same error in ollama 0.20.3

GiteaMirror commented 2026-04-22 12:56:03 -05:00

Author

Owner

Copy Link

@SamLebarbare commented on GitHub (Apr 16, 2026):

We are using multilingual-e5-large and we are seeing the same issue. I assume switching to another model might work around it, but changing an embedding model has significant implications. Keeping Ollama up to date is also very important for us. It would be great to get this bug fixed.

<!-- gh-comment-id:4258534315 --> @SamLebarbare commented on GitHub (Apr 16, 2026): We are using multilingual-e5-large and we are seeing the same issue. I assume switching to another model might work around it, but changing an embedding model has significant implications. Keeping Ollama up to date is also very important for us. It would be great to get this bug fixed.

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

main

mxyng/docs-cloud

parth-update-hermes-launch

hoyyeva/vscode-extension-docs-update

parth-gemma4-chat-template-renderer

parth-api-status-context-length

hoyyeva/wire-up-context-length

hoyyeva/claude-code-context-doc

jmorganca/investigate-issue-17046

hoyyeva/hermes-docs

jmorganca/agent-loop-style

hoyyeva/openclaw

parth-agent-loop

hoyyeva/ollama-vscode-extension

brucemacd/cache-metrics

brucemacd/hermes-desktop

hoyyeva/docs-vscode

parth-input-style-experiment

brucemacd/docs-glm52

hoyyeva/poc-docs

Parth/mlx-launch-recommendations

parth-first-time-app-cli-experience

test/darwin-xcode-pin

improve-cloud-model-recommendations

hoyyeva/goose-docs

jmorganca/context-limit-fixes

hoyyeva/qwen-doc

hoyyeva/vscode-docs

jmorganca/remove-mlx-imagegen-code

parth-copilot-token-length-defaults

hoyyeva/poolside-windows

laguna-support

jmorganca/harden-markdown-rendering

laguna-renderer-parser

laguna-llamacpp

codex/make-integration-hidden-and-lunchable

brucemacd/omp-docs

pdevine/gguf-mtp-oldstyle

hoyyeva/migrate-pi

hoyyeva/anthropic-local-image-path

parth-launch-codex-app

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth/hide-claude-desktop-till-release

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

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

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

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

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

v0.32.1

v0.32.1-rc0

v0.32.0

v0.32.0-rc0

v0.31.2

v0.31.2-rc2

v0.31.2-rc1

v0.31.2-rc0

v0.31.1

v0.31.0

v0.30.12-rc0

v0.30.11

v0.30.11-rc1

v0.30.11-rc0

v0.30.10

v0.30.10-rc1

v0.30.10-rc0

v0.30.9

v0.30.9-rc2

v0.30.9-rc1

v0.30.9-rc0

v0.30.8

v0.30.8-rc0

v0.30.7

v0.30.7-rc1

v0.30.7-rc0

v0.30.6

v0.30.6-rc0

v0.30.5

v0.30.5-rc0

v0.30.4

v0.30.4-rc1

v0.30.4-rc0

v0.30.3

v0.30.2

v0.30.2-rc0

v0.30.1

v0.30.1-rc0

v0.30.0

v0.30.0-rc32

v0.30.0-rc31

v0.30.0-rc30

v0.30.0-rc29

v0.30.0-rc28

v0.30.0-rc27

v0.30.0-rc26

v0.30.0-rc25

v0.30.0-rc24

v0.30.0-rc23

v0.30.0-rc22

v0.30.0-rc21

v0.30.0-rc20

v0.30.0-rc19

v0.30.0-rc18

v0.25.0-rc0

v0.30.0-rc17

v0.30.0-rc16

v0.24.0-rc1

v0.24.0

v0.24.0-rc0

v0.23.4

v0.23.4-rc0

v0.30.0-rc15

v0.23.3

v0.23.3-rc1

v0.30.0-rc14

v0.23.3-rc0

v0.30.0-rc13

v0.30.0-rc12

v0.30.0-rc11

v0.30.0-rc10

v0.30.0-rc9

v0.30.0-rc8

v0.30.0-rc7

v0.30.0-rc6

v0.30.0-rc5

v0.23.2

v0.23.2-rc0

v0.30.0-rc4

v0.30.0-rc3

v0.30.0-rc2

v0.30.0-rc1

v0.30.0-rc0

v0.23.1

v0.23.1-rc0

v0.23.0

v0.23.0-rc0

v0.22.1

v0.22.1-rc1

v0.22.1-rc0

v0.22.0

v0.22.0-rc1

v0.21.3-rc0

v0.21.2-rc1

v0.21.2

v0.21.2-rc0

v0.21.1

v0.21.1-rc1

v0.21.1-rc0

v0.21.0

v0.21.0-rc1

v0.21.0-rc0

v0.20.8-rc0

v0.20.7

v0.20.7-rc1

v0.20.7-rc0

v0.20.6

v0.20.6-rc1

v0.20.6-rc0

v0.20.5

v0.20.5-rc2

v0.20.5-rc1

v0.20.5-rc0

v0.20.4

v0.20.4-rc2

v0.20.4-rc1

v0.20.4-rc0

v0.20.3

v0.20.3-rc0

v0.20.2

v0.20.1

v0.20.1-rc2

v0.20.1-rc1

v0.20.1-rc0

v0.20.0

v0.20.0-rc1

v0.20.0-rc0

v0.19.0

v0.19.0-rc2

v0.19.0-rc1

v0.19.0-rc0

v0.18.4-rc1

v0.18.4-rc0

v0.18.3

v0.18.3-rc2

v0.18.3-rc1

v0.18.3-rc0

v0.18.2

v0.18.2-rc1

v0.18.2-rc0

v0.18.1

v0.18.1-rc1

v0.18.1-rc0

v0.18.0

v0.18.0-rc2

v0.18.0-rc1

v0.18.0-rc0

v0.17.8-rc4

v0.17.8-rc3

v0.17.8-rc2

v0.17.8-rc1

v0.17.8-rc0

v0.17.7

v0.17.7-rc2

v0.17.7-rc1

v0.17.7-rc0

v0.17.6

v0.17.5

v0.17.4

v0.17.3

v0.17.2

v0.17.1

v0.17.1-rc2

v0.17.1-rc1

v0.17.1-rc0

v0.17.0

v0.17.0-rc2

v0.17.0-rc1

v0.17.0-rc0

v0.16.3

v0.16.3-rc2

v0.16.3-rc1

v0.16.3-rc0

v0.16.2

v0.16.2-rc0

v0.16.1

v0.16.0

v0.16.0-rc2

v0.16.0-rc0

v0.16.0-rc1

v0.15.6

v0.15.5

v0.15.5-rc5

v0.15.5-rc4

v0.15.5-rc3

v0.15.5-rc2

v0.15.5-rc1

v0.15.5-rc0

v0.15.4

v0.15.3

v0.15.2

v0.15.1

v0.15.1-rc1

v0.15.1-rc0

v0.15.0-rc6

v0.15.0

v0.15.0-rc5

v0.15.0-rc4

v0.15.0-rc3

v0.15.0-rc2

v0.15.0-rc1

v0.15.0-rc0

v0.14.3

v0.14.3-rc3

v0.14.3-rc2

v0.14.3-rc1

v0.14.3-rc0

v0.14.2

v0.14.2-rc1

v0.14.2-rc0

v0.14.1

v0.14.0-rc11

v0.14.0

v0.14.0-rc10

v0.14.0-rc9

v0.14.0-rc8

v0.14.0-rc7

v0.14.0-rc6

v0.14.0-rc5

v0.14.0-rc4

v0.14.0-rc3

v0.14.0-rc2

v0.14.0-rc1

v0.14.0-rc0

v0.13.5

v0.13.5-rc1

v0.13.5-rc0

v0.13.4-rc2

v0.13.4

v0.13.4-rc1

v0.13.4-rc0

v0.13.3

v0.13.3-rc1

v0.13.3-rc0

v0.13.2

v0.13.2-rc2

v0.13.2-rc1

v0.13.2-rc0

v0.13.1

v0.13.1-rc2

v0.13.1-rc1

v0.13.1-rc0

v0.13.0

v0.13.0-rc0

v0.12.11

v0.12.11-rc1

v0.12.11-rc0

v0.12.10

v0.12.10-rc1

v0.12.10-rc0

v0.12.9-rc0

v0.12.9

v0.12.8

v0.12.8-rc0

v0.12.7

v0.12.7-rc1

v0.12.7-rc0

v0.12.7-citest0

v0.12.6

v0.12.6-rc1

v0.12.6-rc0

v0.12.5

v0.12.5-rc0

v0.12.4

v0.12.4-rc7

v0.12.4-rc6

v0.12.4-rc5

v0.12.4-rc4

v0.12.4-rc3

v0.12.4-rc2

v0.12.4-rc1

v0.12.4-rc0

v0.12.3

v0.12.2

v0.12.2-rc0

v0.12.1

v0.12.1-rc1

v0.12.1-rc2

v0.12.1-rc0

v0.12.0

v0.12.0-rc1

v0.12.0-rc0

v0.11.11

v0.11.11-rc3

v0.11.11-rc2

v0.11.11-rc1

v0.11.11-rc0

v0.11.10

v0.11.9

v0.11.9-rc0

v0.11.8

v0.11.8-rc0

v0.11.7-rc1

v0.11.7-rc0

v0.11.7

v0.11.6

v0.11.6-rc0

v0.11.5-rc4

v0.11.5-rc3

v0.11.5

v0.11.5-rc5

v0.11.5-rc2

v0.11.5-rc1

v0.11.5-rc0

v0.11.4

v0.11.4-rc0

v0.11.3

v0.11.3-rc0

v0.11.2

v0.11.1

v0.11.0-rc0

v0.11.0-rc1

v0.11.0-rc2

v0.11.0

v0.10.2-int1

v0.10.1

v0.10.0

v0.10.0-rc4

v0.10.0-rc3

v0.10.0-rc2

v0.10.0-rc1

v0.10.0-rc0

v0.9.7-rc1

v0.9.7-rc0

v0.9.6

v0.9.6-rc0

v0.9.6-ci0

v0.9.5

v0.9.4-rc5

v0.9.4-rc6

v0.9.4

v0.9.4-rc3

v0.9.4-rc4

v0.9.4-rc1

v0.9.4-rc2

v0.9.4-rc0

v0.9.3

v0.9.3-rc5

v0.9.4-citest0

v0.9.3-rc4

v0.9.3-rc3

v0.9.3-rc2

v0.9.3-rc1

v0.9.3-rc0

v0.9.2

v0.9.1

v0.9.1-rc1

v0.9.1-rc0

v0.9.1-ci1

v0.9.1-ci0

v0.9.0

v0.9.0-rc0

v0.8.0

v0.8.0-rc0

v0.7.1-rc2

v0.7.1

v0.7.1-rc1

v0.7.1-rc0

v0.7.0

v0.7.0-rc1

v0.7.0-rc0

v0.6.9-rc0

v0.6.8

v0.6.8-rc0

v0.6.7

v0.6.7-rc2

v0.6.7-rc1

v0.6.7-rc0

v0.6.6

v0.6.6-rc2

v0.6.6-rc1

v0.6.6-rc0

v0.6.5-rc1

v0.6.5

v0.6.5-rc0

v0.6.4-rc0

v0.6.4

v0.6.3-rc1

v0.6.3

v0.6.3-rc0

v0.6.2

v0.6.2-rc0

v0.6.1

v0.6.1-rc0

v0.6.0-rc0

v0.6.0

v0.5.14-rc0

v0.5.13

v0.5.13-rc6

v0.5.13-rc5

v0.5.13-rc4

v0.5.13-rc3

v0.5.13-rc2

v0.5.13-rc1

v0.5.13-rc0

v0.5.12

v0.5.12-rc1

v0.5.12-rc0

v0.5.11

v0.5.10

v0.5.9

v0.5.9-rc0

v0.5.8-rc13

v0.5.8

v0.5.8-rc12

v0.5.8-rc11

v0.5.8-rc10

v0.5.8-rc9

v0.5.8-rc8

v0.5.8-rc7

v0.5.8-rc6

v0.5.8-rc5

v0.5.8-rc4

v0.5.8-rc3

v0.5.8-rc2

v0.5.8-rc1

v0.5.8-rc0

v0.5.7

v0.5.6

v0.5.5

v0.5.5-rc0

v0.5.4

v0.5.3

v0.5.3-rc0

v0.5.2

v0.5.2-rc3

v0.5.2-rc2

v0.5.2-rc1

v0.5.2-rc0

v0.5.1

v0.5.0

v0.5.0-rc1

v0.4.8-rc0

v0.4.7

v0.4.6

v0.4.5

v0.4.4

v0.4.3

v0.4.3-rc0

v0.4.2

v0.4.2-rc1

v0.4.2-rc0

v0.4.1

v0.4.1-rc0

v0.4.0

v0.4.0-rc8

v0.4.0-rc7

v0.4.0-rc6

v0.4.0-rc5

v0.4.0-rc4

v0.4.0-rc3

v0.4.0-rc2

v0.4.0-rc1

v0.4.0-rc0

v0.4.0-ci3

v0.3.14

v0.3.14-rc0

v0.3.13

v0.3.12

v0.3.12-rc5

v0.3.12-rc4

v0.3.12-rc3

v0.3.12-rc2

v0.3.12-rc1

v0.3.11

v0.3.11-rc4

v0.3.11-rc3

v0.3.11-rc2

v0.3.11-rc1

v0.3.10

v0.3.10-rc1

v0.3.9

v0.3.8

v0.3.7

v0.3.7-rc6

v0.3.7-rc5

v0.3.7-rc4

v0.3.7-rc3

v0.3.7-rc2

v0.3.7-rc1

v0.3.6

v0.3.5

v0.3.4

v0.3.3

v0.3.2

v0.3.1

v0.3.0

v0.2.8

v0.2.8-rc2

v0.2.8-rc1

v0.2.7

v0.2.6

v0.2.5

v0.2.4

v0.2.3

v0.2.2

v0.2.2-rc2

v0.2.2-rc1

v0.2.1

v0.2.0

v0.1.49-rc14

v0.1.49-rc13

v0.1.49-rc12

v0.1.49-rc11

v0.1.49-rc10

v0.1.49-rc9

v0.1.49-rc8

v0.1.49-rc7

v0.1.49-rc6

v0.1.49-rc4

v0.1.49-rc5

v0.1.49-rc3

v0.1.49-rc2

v0.1.49-rc1

v0.1.48

v0.1.47

v0.1.46

v0.1.45-rc5

v0.1.45

v0.1.45-rc4

v0.1.45-rc3

v0.1.45-rc2

v0.1.45-rc1

v0.1.44

v0.1.43

v0.1.42

v0.1.41

v0.1.40

v0.1.40-rc1

v0.1.39

v0.1.39-rc2

v0.1.39-rc1

v0.1.38

v0.1.37

v0.1.36

v0.1.35

v0.1.35-rc1

v0.1.34

v0.1.34-rc1

v0.1.33

v0.1.33-rc7

v0.1.33-rc6

v0.1.33-rc5

v0.1.33-rc4

v0.1.33-rc3

v0.1.33-rc2

v0.1.33-rc1

v0.1.32

v0.1.32-rc2

v0.1.32-rc1

v0.1.31

v0.1.30

v0.1.29

v0.1.28

v0.1.27

v0.1.26

v0.1.25

v0.1.24

v0.1.23

v0.1.22

v0.1.21

v0.1.20

v0.1.19

v0.1.18

v0.1.17

v0.1.16

v0.1.15

v0.1.14

v0.1.13

v0.1.12

v0.1.11

v0.1.10

v0.1.9

v0.1.8

v0.1.7

v0.1.6

v0.1.5

v0.1.4

v0.1.3

v0.1.2

v0.1.1

v0.1.0

v0.0.21

v0.0.20

v0.0.19

v0.0.18

v0.0.17

v0.0.16

v0.0.15

v0.0.14

v0.0.13

v0.0.12

v0.0.11

v0.0.10

v0.0.9

v0.0.8

v0.0.7

v0.0.6

v0.0.5

v0.0.4

v0.0.3

v0.0.2

v0.0.1

Labels

Clear labels

amd

api

app

bug

build

cli

cloud

compatibility

context-length

create

docker

documentation

embeddings

feature request

feedback wanted

good first issue

gpt-oss

gpu

harmony

help wanted

image

install

intel

js

launch

linux

macos

memory

mlx

model

needs more info

networking

nvidia

ollama.com

performance

pull-request

Mirrored from GitHub Pull Request

python

question

registry

rendering

thinking

tools

top

vulkan

windows

wsl

No Label bug

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

GiteaMirror ninjasurge

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#32050