Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Hmm. Interesting question. We had no issues using Mixtral 8x7B for this, perhaps reinforcing your point. We use fine-tuned Mistral-7B instances but not for long context stuff.

Maybe a neat eval to try.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: