peft
https://github.com/huggingface/peft
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
not yet supported1 Subscribers
Add a CodeTriage badge to peft
Help out
- Issues
- CI: Fix failing torchao test
- Adding CorDA as an optional initialization method of LoRA
- FIX: Prevent CUDA context initialization due to AWQ
- Update CPT documentation
- Bug: BOFT forward/merging with CUDA
- FIX: Avoid needless copy from modules_to_save
- 训练时使用的QLoRA 4rank,进行cuda模型合并导出时出现,KeyError: 'base_model.model.model.model.layers.14.mlp.down_proj'
- Documentation for LoRAConfig.
- modules_to_save Incorrect Overlap in Multiple LoRA Adapters
- KeyError: Parameter containing
- Docs
- not yet supported