google-deepmind / google-deepmind/gemma
Finetuning script for Gemma3
Open
Showcase
- Dominant language
- Python
- Stars
- 5.7k
- Forks
- 1k
- Avg merge
- 10h 33m
- Merged PRs (30d)
- 2
Description
https://github.com/2U1/Gemma3-Finetune
I made a code for who wants to use the huggingface version to finetune, and having difficult using some other frameworks like me.
This code only uses huggingface for fine-tuning the 4B, 12B and 27B.
Also, you can set different learning_rate for vision_tower and language_model. ( Also for the projector)
Feedback and issues are welcome!
Contributor guide
Assessment
This issue has not been assessed yet.