Derek Lewis comments

Repositories
Issues
Comments

Results 2 comments of


                                            Derek Lewis

Using PEFT causes model to not predict EOS

Running into this issue myself with 'all-linear' and SFTTrainer using peft main, transformers 4.40.2, and trl 0.8.6. No PEFT and EOS is predicted fine. w/ PEFT and EOS is not...

Using PEFT causes model to not predict EOS

@BenjaminBossan see below. Tried to simplify as much as possible. Also uploaded fine-tuned models to hub w/ PEFT enabled & disabled. TRL seems to be having some issues w/ chat_templates...