github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9049] Long system prompt results in model does not answer question according to prompt content. #31650

New Issue
Closed
opened 2026-04-22 12:18:23 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 12:18:23 -05:00
Owner
Copy Link

Originally created by @netspym on GitHub (Feb 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9049

What is the issue?

Has anyone recently deployed ollama on Ubuntu? I've noticed that no matter which model I use, including qwen, deepseek, and phi4 (fp16 full model), if the system prompt I give it is too long, it doesn't respond according to the content of the system prompt. It only works properly if the system prompt is within 100 characters. Has anyone else encountered this issue? Thanks.

num_ctx is already set at 100000 big enough.
data = {"model": llm_model_name, "messages": messages, "temperature": 0.3, "num_ctx": 1000000, "keep_alive": -1}
data_json = json.dumps(data, ensure_ascii=False)
headers = {'Content-Type': 'application/json'}

Relevant log output

OS

Linux

GPU

No response

CPU

AMD

Ollama version

0.5.7

Originally created by @netspym on GitHub (Feb 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9049 ### What is the issue? Has anyone recently deployed ollama on Ubuntu? I've noticed that no matter which model I use, including qwen, deepseek, and phi4 (fp16 full model), if the system prompt I give it is too long, it doesn't respond according to the content of the system prompt. It only works properly if the system prompt is within 100 characters. Has anyone else encountered this issue? Thanks. num_ctx is already set at 100000 big enough. data = {"model": llm_model_name, "messages": messages, "temperature": 0.3, "num_ctx": 1000000, "keep_alive": -1} data_json = json.dumps(data, ensure_ascii=False) headers = {'Content-Type': 'application/json'} ### Relevant log output ```shell ``` ### OS Linux ### GPU _No response_ ### CPU AMD ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-22 12:18:23 -05:00
GiteaMirror commented 2026-04-22 12:18:25 -05:00
Author
Owner
Copy Link

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

Server logs will aid in debugging.

<!-- gh-comment-id:2654155814 --> @rick-github commented on GitHub (Feb 12, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging.
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#31650
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?