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
- prepare_model_for_kbit_training adds ~1 GB CUDA reserved memory in 500 ms — undocumented cost that breaks memory-constrained training on 8 GB unified-memory devices
- Mica
- Add UniLora tuner to PEFT
- Fail loud on save_pretrained() for unsharded LoRA tensors
- FIX BdLoraConfig.nblocks default value
- [Proposal] Add FRoD tuner for full-rank parameter-efficient fine-tuning
- [BUG] peft 0.19 diffusers LoRA Index Error.
- [BUG] peft 0.19 target_modules (str) use `set`
- FIX Resolve regex target_modules in MoE config conversion
- FIX BEFT merge on bias-less layers; RandLoRA save_projection default
- Docs
- not yet supported