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 #4811] ollama qwen long text problem #28797

New Issue
Open
opened 2026-04-22 07:20:29 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 07:20:29 -05:00
Owner
Copy Link

Originally created by @kaka2008 on GitHub (Jun 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4811

What is the issue?

When I Use ollama, deploy qwen:110b-chat-v1.5-q6_K model

When the context (Chinese) exceeds around 3000 characters (not precise), it fails to recognize the system prompt.

I tried increasing num_ctx to 32768 or max_tokens to 32768 through calling ollama itself or via the OpenAI API, but neither had any effect.

I saw someone mention setting a dynamic factor, but couldn't find where to set it in ollama.

How can I resolve this issue? Thank you.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.33

Originally created by @kaka2008 on GitHub (Jun 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4811 ### What is the issue? When I Use ollama, deploy [qwen:110b-chat-v1.5-q6_K](https://ollama.com/library/qwen:110b-chat-v1.5-q5_K_M) model When the context (Chinese) exceeds around 3000 characters (not precise), it fails to recognize the system prompt. I tried increasing num_ctx to 32768 or max_tokens to 32768 through calling ollama itself or via the OpenAI API, but neither had any effect. I saw someone mention setting a dynamic factor, but couldn't find where to set it in ollama. How can I resolve this issue? Thank you. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.33
GiteaMirror added the bug label 2026-04-22 07:20:29 -05:00
GiteaMirror commented 2026-04-22 07:20:30 -05:00
Author
Owner
Copy Link

@fjesikfjdskl commented on GitHub (Aug 8, 2024):

+1

<!-- gh-comment-id:2275150823 --> @fjesikfjdskl commented on GitHub (Aug 8, 2024): +1
GiteaMirror commented 2026-04-22 07:20:31 -05:00
Author
Owner
Copy Link

@goactiongo commented on GitHub (Oct 11, 2024):

the same issue，#7146

It's ok for recognizing short text content, but failed to recognize the long text content.

<!-- gh-comment-id:2407296093 --> @goactiongo commented on GitHub (Oct 11, 2024): the same issue，#7146 It's ok for recognizing short text content, but failed to recognize the long text content.
GiteaMirror commented 2026-04-22 07:20:32 -05:00
Author
Owner
Copy Link

@goactiongo commented on GitHub (Oct 12, 2024):

#7146

If I place the content of the document in the HUMAN prompt (previously placed in the SYSTEM prompt), ollama can correctly recognize and summarize the document content.
you have a try and discuss continue with me ,pls

<!-- gh-comment-id:2408361604 --> @goactiongo commented on GitHub (Oct 12, 2024): #7146 If I place the content of the document in the HUMAN prompt (previously placed in the SYSTEM prompt), ollama can correctly recognize and summarize the document content. you have a try and discuss continue with me ,pls
GiteaMirror commented 2026-04-22 07:20:33 -05:00
Author
Owner
Copy Link

@dfrrk commented on GitHub (Oct 17, 2024):

我把上下文长度调成85000可以处理1.3万个字符，用的是(qwen2.5:3b-instruct)模型，供你参考

<!-- gh-comment-id:2419996400 --> @dfrrk commented on GitHub (Oct 17, 2024): 我把上下文长度调成85000可以处理1.3万个字符，用的是(qwen2.5:3b-instruct)模型，供你参考
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#28797
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?