Julien Fleury comments

Repositories
Issues
Comments

Results 2 comments of


                                            Julien Fleury

Is there a way to fine tune the llama.7B model?

https://github.com/tloen/alpaca-lora with a few changes seem to be a good option. (Just by changing the generate_prompt to something more chat conversation oriented than instructions oriented). https://github.com/deep-diver/Alpaca-LoRA-Serve is also a good...

Is there a way to fine tune the llama.7B model?

@mouchourider this is issue https://github.com/cocktailpeanut/dalai/issues/135