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 #2901] The local running model repeatedly cycles through its response to the first question, disregarding any subsequent input. #48288

New Issue
Closed
opened 2026-04-28 07:36:08 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-28 07:36:08 -05:00
Owner
Copy Link

Originally created by @Yanxxx on GitHub (Mar 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2901

Installed ollama client from https://ollama.com/download.
OS： Windows 11 pro
Model: ollama run gemma:7b
Question asked: 你和Gemini有什么区别
The output text always focus on the difference between Gemini and Gemma. However the answer is not right either. It keeps saying that Gemini was developed by OpenAI.

Originally created by @Yanxxx on GitHub (Mar 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2901 Installed ollama client from https://ollama.com/download. OS： Windows 11 pro Model: ollama run gemma:7b Question asked: 你和Gemini有什么区别 The output text always focus on the difference between Gemini and Gemma. However the answer is not right either. It keeps saying that Gemini was developed by OpenAI.
GiteaMirror commented 2026-04-28 07:36:09 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Mar 3, 2024):

Are you using the latest version of Ollama (0.1.27)? Have you ollama pull gemma:7b model recently? There was some trouble with the model in earlier versions.

<!-- gh-comment-id:1975382968 --> @easp commented on GitHub (Mar 3, 2024): Are you using the latest version of Ollama (0.1.27)? Have you `ollama pull gemma:7b` model recently? There was some trouble with the model in earlier versions.
GiteaMirror commented 2026-04-28 07:36:09 -05:00
Author
Owner
Copy Link

@Yanxxx commented on GitHub (Mar 4, 2024):

Are you using the latest version of Ollama (0.1.27)? Have you ollama pull gemma:7b model recently? There was some trouble with the model in earlier versions.

Yes, I downloaded it today. And one more thing. I closed the terminal and cannot open it again.

<!-- gh-comment-id:1975444052 --> @Yanxxx commented on GitHub (Mar 4, 2024): > Are you using the latest version of Ollama (0.1.27)? Have you `ollama pull gemma:7b` model recently? There was some trouble with the model in earlier versions. Yes, I downloaded it today. And one more thing. I closed the terminal and cannot open it again.
GiteaMirror commented 2026-04-28 07:36:09 -05:00
Author
Owner
Copy Link

@Yanxxx commented on GitHub (Mar 4, 2024):

Are you using the latest version of Ollama (0.1.27)? Have you ollama pull gemma:7b model recently? There was some trouble with the model in earlier versions.

I'm uncertain whether this is merely a bug on my computer or if it could be replicated, but this is the situation I encountered.

<!-- gh-comment-id:1975450819 --> @Yanxxx commented on GitHub (Mar 4, 2024): > Are you using the latest version of Ollama (0.1.27)? Have you `ollama pull gemma:7b` model recently? There was some trouble with the model in earlier versions. I'm uncertain whether this is merely a bug on my computer or if it could be replicated, but this is the situation I encountered.
GiteaMirror commented 2026-04-28 07:36:09 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (May 18, 2024):

I tried this on both Mac and Windows 11. I believe it's working as intended. The model definitely has some issues with hallucinations :-D

<!-- gh-comment-id:2118613303 --> @pdevine commented on GitHub (May 18, 2024): I tried this on both Mac and Windows 11. I *believe* it's working as intended. The model definitely has some issues with hallucinations :-D
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
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#48288
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?