Thaweewat

/

typhoon-7b-chat-alpaca

like 4

I used my own PEFT and TRL pipeline with a bit of adjustment for the Mistral architecture. I haven't had time to clean it up for public release yet, but I found this blog that uses a similar pipeline to mine, complete with full explanations, which might be useful:

https://blog.neuralwork.ai/an-llm-fine-tuning-cookbook-with-mistral-7b/