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 #4054] llama-3-chinese-8b-instruct model infinite loop generate & cannot stop #64554

New Issue
Closed
opened 2026-05-03 18:07:07 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 18:07:07 -05:00
Owner
Copy Link

Originally created by @gavinliu on GitHub (Apr 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4054

What is the issue?

Hey, I found an issue of infinite generation that cannot be stopped, when deploying a Chinese fine-tuned model of llama3

How to solve this problem?

Modelfile file:

FROM /llama-3-chinese-8b-instruct/ggml-model-q8_0.gguf
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
SYSTEM """"""
PARAMETER num_keep 24
PARAMETER stop <|start_header_id|>
PARAMETER stop <|end_header_id|>
PARAMETER stop <|eot_id|>
PARAMETER stop assistant

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.32

Originally created by @gavinliu on GitHub (Apr 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4054 ### What is the issue? Hey, I found an issue of infinite generation that cannot be stopped, when deploying a [Chinese fine-tuned model of llama3 ](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-gguf) How to solve this problem? Modelfile file: ```Modelfile FROM /llama-3-chinese-8b-instruct/ggml-model-q8_0.gguf TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" SYSTEM """""" PARAMETER num_keep 24 PARAMETER stop <|start_header_id|> PARAMETER stop <|end_header_id|> PARAMETER stop <|eot_id|> PARAMETER stop assistant ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-05-03 18:07:07 -05:00
GiteaMirror commented 2026-05-03 18:07:09 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Apr 30, 2024):

Can you try running it in the REPL and adding:

/set parameter stop <|reserved_special_token

(without the trailing >)

<!-- gh-comment-id:2086653525 --> @pdevine commented on GitHub (Apr 30, 2024): Can you try running it in the REPL and adding: ``` /set parameter stop <|reserved_special_token ``` (without the trailing >)
GiteaMirror commented 2026-05-03 18:07:10 -05:00
Author
Owner
Copy Link

@gavinliu commented on GitHub (May 24, 2024):

0.1.33 is fix

<!-- gh-comment-id:2128277010 --> @gavinliu commented on GitHub (May 24, 2024): 0.1.33 is fix
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#64554
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?