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
- fix(tuners/lora/bnb): normalize output device for CPU-offloaded BnB layers
- Use _cast_input_dtype in poly Linear.forward
- Use _cast_input_dtype in vera Linear.forward
- LoRA + BnB INT8 + CPU offload: output tensor on wrong device in tuners/lora/bnb.py
- Use _cast_input_dtype in FourierFTLinear.forward
- Fix DeloraLinear.unmerge subtracting un-cast delta weight
- Implement VeLoRA and add tests.
- Fix C3ALinear.forward chaining active adapters through x instead of summing
- Fix OFT Conv2d weight reshaping for non-square kernels
- FIX IA3 _ConvNd.unmerge bias uses torch.mul instead of torch.div
- Docs
- not yet supported