@lumpenspace Even mixtral and 405 base do it (and I suspect every other new base model). If Mistral (instruct?) doesn't do it, it's an interesting anomaly.And what you're saying is obvious, and half useless. Obviously no one statement can address everything going on.https://t.co/1IfV6UBDim
cited on: mixtral-8x7b
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.