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

[GH-ISSUE #2839] keeps loading but never success #1725

New Issue
Open
opened 2026-04-12 11:42:14 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 11:42:14 -05:00
Owner
Copy Link

Originally created by @xudong2019 on GitHub (Feb 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2839

ollama run renxin_query_type_classify "hello"
image

I successfully generate a model from gguf file. however keeps loading but never succeed... Any idea what's happening?

FROM ./model_query_type_classify.gguf
PARAMETER temperature 0
SYSTEM """
classify user type
"""

Originally created by @xudong2019 on GitHub (Feb 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2839 ollama run renxin_query_type_classify "hello" ![image](https://github.com/ollama/ollama/assets/16278392/a7ee2375-3493-4d41-b5a6-aa4481e53baf) I successfully generate a model from gguf file. however keeps loading but never succeed... Any idea what's happening? FROM ./model_query_type_classify.gguf PARAMETER temperature 0 SYSTEM """ classify user type """
GiteaMirror added the createbug labels 2026-04-12 11:42:14 -05:00
GiteaMirror commented 2026-04-12 11:42:16 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 29, 2024):

Hi there, sorry this happened. Would it be possible to check the logs for an error?

<!-- gh-comment-id:1971643647 --> @jmorganca commented on GitHub (Feb 29, 2024): Hi there, sorry this happened. Would it be possible to [check the logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) for an error?
GiteaMirror commented 2026-04-12 11:42:16 -05:00
Author
Owner
Copy Link

@xudong2019 commented on GitHub (Mar 1, 2024):

I couldn't identify any error recorded in the log file. I'm running ollama in the docker and used "docker logs 1001d164775c" for the log file.

Here are a few contents in the log file, but no error message identified...
llama_new_context_with_model: freq_scale = 1
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: yes
ggml_init_cublas: CUDA_USE_TENSOR_CORES: no
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
llama_kv_cache_init: CUDA0 KV buffer size = 1600.00 MiB
llama_new_context_with_model: KV self size = 1600.00 MiB, K (f16): 800.00 MiB, V (f16): 800.00 MiB
llama_new_context_with_model: CUDA_Host input buffer size = 15.02 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 307.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 10.00 MiB
llama_new_context_with_model: graph splits (measure): 3
time=2024-03-01T01:34:05.286Z level=INFO source=dyn_ext_server.go:161 msg="Starting llama main loop"
time=2024-03-01T01:34:05.289Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:34:07 |^[[97;42m 200 ^[[0m| 7.799372595s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:34:09 |^[[97;42m 200 ^[[0m| 1.921034882s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:35:11.330Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:35:14 |^[[97;42m 200 ^[[0m| 2.714265698s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:35:16 |^[[97;42m 200 ^[[0m| 2.700883398s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:35:37.347Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:35:39 |^[[97;42m 200 ^[[0m| 1.983048092s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:35:41 |^[[97;42m 200 ^[[0m| 2.288229176s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:35:52.671Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:35:54 |^[[97;42m 200 ^[[0m| 2.117185287s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:35:57 |^[[97;42m 200 ^[[0m| 2.741038553s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:37:24.107Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:37:26 |^[[97;42m 200 ^[[0m| 2.556465865s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:37:29 |^[[97;42m 200 ^[[0m| 2.56224256s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:39:57.186Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:39:58 |^[[97;42m 200 ^[[0m| 1.7195883s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:40:01 |^[[97;42m 200 ^[[0m| 1.606466082s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:41:39.096Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:41:40 |^[[97;42m 200 ^[[0m| 1.688323303s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:41:42 |^[[97;42m 200 ^[[0m| 1.699074626s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:44:01.447Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:44:03 |^[[97;42m 200 ^[[0m| 2.011641752s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:44:05 |^[[97;42m 200 ^[[0m| 1.939643832s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:45:39.781Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images"
[GIN] 2024/03/01 - 01:45:41 |^[[97;42m 200 ^[[0m| 1.913668125s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:45:44 |^[[97;42m 200 ^[[0m| 2.054726132s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"

and earlier:

llama_new_context_with_model: CUDA_Host input buffer size = 15.02 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 307.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 10.00 MiB
llama_new_context_with_model: graph splits (measure): 3
time=2024-03-01T01:28:39.193Z level=INFO source=dyn_ext_server.go:161 msg="Starting llama main loop"
[GIN] 2024/03/01 - 01:28:41 |^[[97;42m 200 ^[[0m| 7.861097766s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
[GIN] 2024/03/01 - 01:29:51 |^[[97;42m 200 ^[[0m| 2.259164053s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat"
[GIN] 2024/03/01 - 01:29:52 |^[[97;42m 200 ^[[0m| 1.839495069s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate"
time=2024-03-01T01:30:25.356Z level=INFO source=routes.go:78 msg="changing loaded model"
time=2024-03-01T01:30:28.171Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-03-01T01:30:28.171Z level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 8.6"
time=2024-03-01T01:30:28.171Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-03-01T01:30:28.171Z level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 8.6"
time=2024-03-01T01:30:28.171Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
loading library /tmp/ollama3442133364/cuda_v11/libext_server.so
time=2024-03-01T01:30:28.171Z level=INFO source=dyn_ext_server.go:90 msg="Loading Dynamic llm server: /tmp/ollama3442133364/cuda_v11/libext_server.so"
time=2024-03-01T01:30:28.171Z level=INFO source=dyn_ext_server.go:150 msg="Initializing llama server"
llama_model_loader: loaded meta data with 24 key-value pairs and 254 tensors from /root/.ollama/models/blobs/sha256:456402914e838a953e0cf80caa6adbe75383d9e63584a964f504a7bbb8f7aad9 (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 = gemma
llama_model_loader: - kv 1: general.name str = gemma-7b-it
llama_model_loader: - kv 2: gemma.context_length u32 = 8192
llama_model_loader: - kv 3: gemma.embedding_length u32 = 3072
llama_model_loader: - kv 4: gemma.block_count u32 = 28
llama_model_loader: - kv 5: gemma.feed_forward_length u32 = 24576
llama_model_loader: - kv 6: gemma.attention.head_count u32 = 16
llama_model_loader: - kv 7: gemma.attention.head_count_kv u32 = 16
llama_model_loader: - kv 8: gemma.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 9: gemma.attention.key_length u32 = 256
llama_model_loader: - kv 10: gemma.attention.value_length u32 = 256
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,256000] = ["", "", "", "", ...
llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,256000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 2

<!-- gh-comment-id:1972489711 --> @xudong2019 commented on GitHub (Mar 1, 2024): I couldn't identify any error recorded in the log file. I'm running ollama in the docker and used "docker logs 1001d164775c" for the log file. Here are a few contents in the log file, but no error message identified... llama_new_context_with_model: freq_scale = 1 ggml_init_cublas: GGML_CUDA_FORCE_MMQ: yes ggml_init_cublas: CUDA_USE_TENSOR_CORES: no ggml_init_cublas: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes llama_kv_cache_init: CUDA0 KV buffer size = 1600.00 MiB llama_new_context_with_model: KV self size = 1600.00 MiB, K (f16): 800.00 MiB, V (f16): 800.00 MiB llama_new_context_with_model: CUDA_Host input buffer size = 15.02 MiB llama_new_context_with_model: CUDA0 compute buffer size = 307.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 10.00 MiB llama_new_context_with_model: graph splits (measure): 3 time=2024-03-01T01:34:05.286Z level=INFO source=dyn_ext_server.go:161 msg="Starting llama main loop" time=2024-03-01T01:34:05.289Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:34:07 |^[[97;42m 200 ^[[0m| 7.799372595s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:34:09 |^[[97;42m 200 ^[[0m| 1.921034882s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:35:11.330Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:35:14 |^[[97;42m 200 ^[[0m| 2.714265698s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:35:16 |^[[97;42m 200 ^[[0m| 2.700883398s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:35:37.347Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:35:39 |^[[97;42m 200 ^[[0m| 1.983048092s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:35:41 |^[[97;42m 200 ^[[0m| 2.288229176s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:35:52.671Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:35:54 |^[[97;42m 200 ^[[0m| 2.117185287s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:35:57 |^[[97;42m 200 ^[[0m| 2.741038553s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:37:24.107Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:37:26 |^[[97;42m 200 ^[[0m| 2.556465865s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:37:29 |^[[97;42m 200 ^[[0m| 2.56224256s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:39:57.186Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:39:58 |^[[97;42m 200 ^[[0m| 1.7195883s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:40:01 |^[[97;42m 200 ^[[0m| 1.606466082s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:41:39.096Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:41:40 |^[[97;42m 200 ^[[0m| 1.688323303s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:41:42 |^[[97;42m 200 ^[[0m| 1.699074626s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:44:01.447Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:44:03 |^[[97;42m 200 ^[[0m| 2.011641752s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:44:05 |^[[97;42m 200 ^[[0m| 1.939643832s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:45:39.781Z level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" [GIN] 2024/03/01 - 01:45:41 |^[[97;42m 200 ^[[0m| 1.913668125s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:45:44 |^[[97;42m 200 ^[[0m| 2.054726132s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" and earlier: llama_new_context_with_model: CUDA_Host input buffer size = 15.02 MiB llama_new_context_with_model: CUDA0 compute buffer size = 307.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 10.00 MiB llama_new_context_with_model: graph splits (measure): 3 time=2024-03-01T01:28:39.193Z level=INFO source=dyn_ext_server.go:161 msg="Starting llama main loop" [GIN] 2024/03/01 - 01:28:41 |^[[97;42m 200 ^[[0m| 7.861097766s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" [GIN] 2024/03/01 - 01:29:51 |^[[97;42m 200 ^[[0m| 2.259164053s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/chat" [GIN] 2024/03/01 - 01:29:52 |^[[97;42m 200 ^[[0m| 1.839495069s | 172.19.0.3 |^[[97;46m POST ^[[0m "/api/generate" time=2024-03-01T01:30:25.356Z level=INFO source=routes.go:78 msg="changing loaded model" time=2024-03-01T01:30:28.171Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-03-01T01:30:28.171Z level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 8.6" time=2024-03-01T01:30:28.171Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-03-01T01:30:28.171Z level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 8.6" time=2024-03-01T01:30:28.171Z level=INFO source=cpu_common.go:11 msg="CPU has AVX2" loading library /tmp/ollama3442133364/cuda_v11/libext_server.so time=2024-03-01T01:30:28.171Z level=INFO source=dyn_ext_server.go:90 msg="Loading Dynamic llm server: /tmp/ollama3442133364/cuda_v11/libext_server.so" time=2024-03-01T01:30:28.171Z level=INFO source=dyn_ext_server.go:150 msg="Initializing llama server" llama_model_loader: loaded meta data with 24 key-value pairs and 254 tensors from /root/.ollama/models/blobs/sha256:456402914e838a953e0cf80caa6adbe75383d9e63584a964f504a7bbb8f7aad9 (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 = gemma llama_model_loader: - kv 1: general.name str = gemma-7b-it llama_model_loader: - kv 2: gemma.context_length u32 = 8192 llama_model_loader: - kv 3: gemma.embedding_length u32 = 3072 llama_model_loader: - kv 4: gemma.block_count u32 = 28 llama_model_loader: - kv 5: gemma.feed_forward_length u32 = 24576 llama_model_loader: - kv 6: gemma.attention.head_count u32 = 16 llama_model_loader: - kv 7: gemma.attention.head_count_kv u32 = 16 llama_model_loader: - kv 8: gemma.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 9: gemma.attention.key_length u32 = 256 llama_model_loader: - kv 10: gemma.attention.value_length u32 = 256 llama_model_loader: - kv 11: tokenizer.ggml.model str = llama llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,256000] = ["<pad>", "<eos>", "<bos>", "<unk>", ... llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,256000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 2
GiteaMirror commented 2026-04-12 11:42:17 -05:00
Author
Owner
Copy Link

@xudong2019 commented on GitHub (Mar 1, 2024):

by the way this is my modelfile

FROM ./model_query_type_classify.gguf
PARAMETER temperature 0
SYSTEM """
classify user input
"""

<!-- gh-comment-id:1972515666 --> @xudong2019 commented on GitHub (Mar 1, 2024): by the way this is my modelfile FROM ./model_query_type_classify.gguf PARAMETER temperature 0 SYSTEM """ classify user input """
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug create
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1725
Delete Branch "%!s()"

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