LC
Leshem Choshen
@lchoshen.bsky.social
148 followers107 following317 posts
Following, we show that loras are not parameter efficient Take a lora➡️throw 80% parameters➡️make it binary➡️ improve result🤯 arxiv.org/abs/2311.13171github.com/zipnn/zipnn
ComPEFT: Compression for Communicating Parameter Efficient Updates...
Parameter-efficient fine-tuning (PEFT) techniques make it possible to efficiently adapt a language model to create "expert" models that specialize to new tasks or domains. Recent techniques in...
You got till here? Great, share some of your thoughts and questions or like🥰
LC
Leshem Choshen
@lchoshen.bsky.social
148 followers107 following317 posts