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

[GH-ISSUE #4907] Cannot run qwen2 7B, 1.5b #65137

New Issue
Closed
opened 2026-05-03 19:50:45 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-03 19:50:45 -05:00
Owner
Copy Link

Originally created by @SAXN-SYNX on GitHub (Jun 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4907

Shows error while running it.

llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen2
llama_model_loader: - kv   1:                               general.name str              = Qwen2-7B-Instruct
llama_model_loader: - kv   2:                          qwen2.block_count u32              = 28
llama_model_loader: - kv   3:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 4
llama_model_loader: - kv   8:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv   9:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  10:                          general.file_type u32              = 2
llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  12:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  17:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  19:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
llama_model_loader: - kv  20:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  141 tensors
llama_model_loader: - type q4_0:  197 tensors
llama_model_loader: - type q6_K:    1 tensors
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'
llama_load_model_from_file: exception loading model
terminate called after throwing an instance of 'std::runtime_error'
  what():  error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.34

Originally created by @SAXN-SYNX on GitHub (Jun 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4907 ### Shows error while running it. ``` llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = qwen2 llama_model_loader: - kv 1: general.name str = Qwen2-7B-Instruct llama_model_loader: - kv 2: qwen2.block_count u32 = 28 llama_model_loader: - kv 3: qwen2.context_length u32 = 32768 llama_model_loader: - kv 4: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 4 llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 10: general.file_type u32 = 2 llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 19: tokenizer.chat_template str = {% for message in messages %}{% if lo... llama_model_loader: - kv 20: general.quantization_version u32 = 2 llama_model_loader: - type f32: 141 tensors llama_model_loader: - type q4_0: 197 tensors llama_model_loader: - type q6_K: 1 tensors llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' llama_load_model_from_file: exception loading model terminate called after throwing an instance of 'std::runtime_error' what(): error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.34
GiteaMirror added the bug label 2026-05-03 19:50:45 -05:00
GiteaMirror commented 2026-05-03 19:50:51 -05:00
Author
Owner
Copy Link

@include commented on GitHub (Jun 7, 2024):

+1.

<!-- gh-comment-id:2155160702 --> @include commented on GitHub (Jun 7, 2024): +1.
GiteaMirror commented 2026-05-03 19:50:51 -05:00
Author
Owner
Copy Link

@boxabirds commented on GitHub (Jun 7, 2024):

Lots of people experiencing this in the Discord.

Happens for me with Ollama 0.1.41 as well.

<!-- gh-comment-id:2155168704 --> @boxabirds commented on GitHub (Jun 7, 2024): Lots of people experiencing this in the Discord. Happens for me with Ollama 0.1.41 as well.
GiteaMirror commented 2026-05-03 19:50:52 -05:00
Author
Owner
Copy Link

@informaticker commented on GitHub (Jun 7, 2024):

Ollama version
0.1.34

Try upgrading first, fixed the issue for me.

<!-- gh-comment-id:2155194676 --> @informaticker commented on GitHub (Jun 7, 2024): > Ollama version > 0.1.34 Try upgrading first, fixed the issue for me.
GiteaMirror commented 2026-05-03 19:50:53 -05:00
Author
Owner
Copy Link

@boxabirds commented on GitHub (Jun 7, 2024):

I get garbage output with 41. image

<!-- gh-comment-id:2155266041 --> @boxabirds commented on GitHub (Jun 7, 2024): I get garbage output with 41. ![image](https://github.com/ollama/ollama/assets/147305/523ea64c-16cb-4670-a590-63871204b723)
GiteaMirror commented 2026-05-03 19:50:55 -05:00
Author
Owner
Copy Link

@iplayfast commented on GitHub (Jun 7, 2024):

I tried running deepseek-v2 (which it pulled and installed) and after that qwen2 started behaving. (could be a clue?)

<!-- gh-comment-id:2155294264 --> @iplayfast commented on GitHub (Jun 7, 2024): I tried running deepseek-v2 (which it pulled and installed) and after that qwen2 started behaving. (could be a clue?)
GiteaMirror commented 2026-05-03 19:50:57 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Jun 7, 2024):

Escreva um código em python para somar os números de 1 até 100.

qwen2:1.5b-instruct 3:12 PM
GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG

image

ollama -v
ollama version is 0.1.41

Open WebUI Versão
v0.2.5

<!-- gh-comment-id:2155301788 --> @ghost commented on GitHub (Jun 7, 2024): Escreva um código em python para somar os números de 1 até 100. qwen2:1.5b-instruct 3:12 PM GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG ![image](https://github.com/ollama/ollama/assets/144032090/7d02fc9d-c100-4dd8-8c13-621f6dba271e) ollama -v ollama version is 0.1.41 Open WebUI Versão v0.2.5
GiteaMirror commented 2026-05-03 19:50:59 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jun 7, 2024):

Hi all, sorry about this. It is fixed in 0.1.42: https://github.com/ollama/ollama/releases/tag/v0.1.42

<!-- gh-comment-id:2155671605 --> @jmorganca commented on GitHub (Jun 7, 2024): Hi all, sorry about this. It is fixed in 0.1.42: https://github.com/ollama/ollama/releases/tag/v0.1.42
GiteaMirror commented 2026-05-03 19:51:00 -05:00
Author
Owner
Copy Link

@liuaifu commented on GitHub (Jun 9, 2024):

@jmorganca

Microsoft Windows [版本 10.0.22631.3593]
(c) Microsoft Corporation。保留所有权利。

C:\Users\laf163>ollama -v
ollama version is 0.1.42

C:\Users\laf163>ollama run qwen2:7b
>>> Why is the sky blue?
#&%$#7456893210

>>> Send a message (/? for help)

NVIDIA GeForce RTX 3050 Laptop GPU

驱动程序版本: 31.0.15.5161
驱动程序日期: 2024/2/15
DirectX 版本: 12 (FL 12.1)
物理位置： PCI 总线 1、设备 0、功能 0

利用率 0%
专用 GPU 内存 0.0/4.0 GB
共享 GPU 内存 0.0/7.7 GB
GPU 内存 0.0/11.7 GB

<!-- gh-comment-id:2156280023 --> @liuaifu commented on GitHub (Jun 9, 2024): @jmorganca ``` Microsoft Windows [版本 10.0.22631.3593] (c) Microsoft Corporation。保留所有权利。 C:\Users\laf163>ollama -v ollama version is 0.1.42 C:\Users\laf163>ollama run qwen2:7b >>> Why is the sky blue? #&%$#7456893210 >>> Send a message (/? for help) ``` NVIDIA GeForce RTX 3050 Laptop GPU 驱动程序版本: 31.0.15.5161 驱动程序日期: 2024/2/15 DirectX 版本: 12 (FL 12.1) 物理位置： PCI 总线 1、设备 0、功能 0 利用率 0% 专用 GPU 内存 0.0/4.0 GB 共享 GPU 内存 0.0/7.7 GB GPU 内存 0.0/11.7 GB
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#65137
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?