how to fine tune this model?

#16
by leo009 - opened

how to fine tune this model?

following this question, how to fine-tune it for particular use cases

Can we use this repo (https://github.com/mistralai/mistral-finetune) to fine-tune it? But I think it's only the LoRA fine-tuning...

But how to structure the data?

Sign up or log in to comment