github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2405] ollama run qwen:0.5B, Reply exception, stuck in a loop. #1399

New Issue
Closed
opened 2026-04-12 11:13:44 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 11:13:44 -05:00
Owner
Copy Link

Originally created by @samzong on GitHub (Feb 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2405

Originally assigned to: @jmorganca on GitHub.

>>> /show info
Model details:
Family              qwen2
Parameter Size      620M
Quantization Level  Q4_0

~ uname -m -s -r
Darwin 23.3.0 arm64

image

https://github.com/ollama/ollama/assets/13782141/746225cc-9147-40e3-b7c3-d40a963fa2d5

/label bug

Originally created by @samzong on GitHub (Feb 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2405 Originally assigned to: @jmorganca on GitHub. ```bash >>> /show info Model details: Family qwen2 Parameter Size 620M Quantization Level Q4_0 ``` ```bash ~ uname -m -s -r Darwin 23.3.0 arm64 ``` ![image](https://github.com/ollama/ollama/assets/13782141/c1bf2750-7093-4b67-85bc-57f9d6afd7d1) https://github.com/ollama/ollama/assets/13782141/746225cc-9147-40e3-b7c3-d40a963fa2d5 /label bug
GiteaMirror added the bug label 2026-04-12 11:13:44 -05:00
GiteaMirror commented 2026-04-12 11:13:46 -05:00
Author
Owner
Copy Link

@bm777 commented on GitHub (Feb 8, 2024):

I had the same behavior with phi2 model. I noticed that the model gives the right or the expected answer before going to a new line (\n). So I had to add "\n" in the stop list.

const stream = await generate({
        model: "phi",
        prompt: text,
        stream: true,
        options: {
            num_predict: 70,
            temperature: 0.65,
            penalize_newline: true,
            top_p: 0.9,
            // presence_penalty: 0.6,
            stop: ["\n", "User:", "Assistant:", "User:"] //["\n"]
        }
    })

It still cuts at a wrong place sometimes, but I can manage to just remove the words after the last punctuation: . or ,
This method will not work if the user ask for a list as a result (give me 3 recipes of cappuccino) -> then after generating the first, the model will try to add a new line for the second element of the list, and it becomes more complicated to control the level.
(any workaround for this use case?)

Screenshot 2024-02-08 at 11 15 00

<!-- gh-comment-id:1933770628 --> @bm777 commented on GitHub (Feb 8, 2024): I had the same behavior with phi2 model. I noticed that the model gives the right or the expected answer before going to a new line (\n). So I had to add "\n" in the stop list. ```js const stream = await generate({ model: "phi", prompt: text, stream: true, options: { num_predict: 70, temperature: 0.65, penalize_newline: true, top_p: 0.9, // presence_penalty: 0.6, stop: ["\n", "User:", "Assistant:", "User:"] //["\n"] } }) ``` It still cuts at a wrong place sometimes, but I can manage to just remove the words after the last punctuation: . or , This method will not work if the user ask for a list as a result (give me 3 recipes of cappuccino) -> then after generating the first, the model will try to add a new line for the second element of the list, and it becomes more complicated to control the level. (any workaround for this use case?) ![Screenshot 2024-02-08 at 11 15 00](https://github.com/ollama/ollama/assets/29865600/19eca312-cc33-4d05-baad-4b994e2ce5ae)
GiteaMirror commented 2026-04-12 11:13:46 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 10, 2024):

The infinite generation should be fixed now. As for the poor responses from smaller models – this may be from the prompt template, prompt or other reasons – all of which we are trying to improve.

<!-- gh-comment-id:2103672593 --> @jmorganca commented on GitHub (May 10, 2024): The infinite generation should be fixed now. As for the poor responses from smaller models – this may be from the prompt template, prompt or other reasons – all of which we are trying to improve.
GiteaMirror commented 2026-04-12 11:13:47 -05:00
Author
Owner
Copy Link

@bm777 commented on GitHub (May 10, 2024):

@jmorganca So we should update the Ollama binary verison then right ?

<!-- gh-comment-id:2104584465 --> @bm777 commented on GitHub (May 10, 2024): @jmorganca So we should update the Ollama binary verison then right ?
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#1399
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?