github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7679] The fine tuned codegemma model exhibits abnormal performance #82583

New Issue
Closed
opened 2026-05-09 15:09:23 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-09 15:09:23 -05:00
Owner
Copy Link

Originally created by @TheSongg on GitHub (Nov 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7679

What is the issue?

I downloaded the codegemma and codellama models from Huggingface and fine tuned them using llama factory. After importing the fine tuned model into Ollama, Codellama works normally, while the Codegemma model seems to have not learned the knowledge of the fine tuned dataset. Similarly, importing the fine tuned codegemma model into llama factory works normally. I have made multiple modifications to the modelfile file when creating the codegemma, but it has not been effective. May I ask what the reason is and how can I resolve it? thank you
ollama：0.4.1
llama factory:0.8.3
codegemma：https://huggingface.co/google/codegemma-7b
codellama：https://huggingface.co/codellama/CodeLlama-7b-hf

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.4.1

Originally created by @TheSongg on GitHub (Nov 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7679 ### What is the issue? I downloaded the codegemma and codellama models from Huggingface and fine tuned them using llama factory. After importing the fine tuned model into Ollama, Codellama works normally, while the Codegemma model seems to have not learned the knowledge of the fine tuned dataset. Similarly, importing the fine tuned codegemma model into llama factory works normally. I have made multiple modifications to the modelfile file when creating the codegemma, but it has not been effective. May I ask what the reason is and how can I resolve it? thank you ollama：0.4.1 llama factory:0.8.3 codegemma：https://huggingface.co/google/codegemma-7b codellama：https://huggingface.co/codellama/CodeLlama-7b-hf ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.1
GiteaMirror added the bug label 2026-05-09 15:09:23 -05:00
GiteaMirror added the needs more info label 2026-05-09 15:13:22 -05:00
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 needs more info
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#82583
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?