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 Trainable Tokens output-head bias
- Four of the five diffusers-style tuner docstring examples (LoHa, LoKr, OFT, MiSS) fail as written
- Add Astra (Activation-Space Tail-Eigenvector LoRA) initialization
- target_modules can match a subset of layers with no warning
- Trainable Tokens drops the output-head bias before merge
- NoRA
- Filter adapter-name slots by tuner-prefix position
- TP + LoRA is broken on transformers 5.16: add_tensor_parallel_hooks_to_module and EmbeddingParallel were removed
- FIX get_layer_device_map StopIteration on CPU-only device maps
- [Bug] Prefix tuning crashes for CPU-only device maps
- Docs
- not yet supported