@jd_pressman 2023-11-05 ♥5 ↻0 original ↗
@teortaxesTex @Teknium1 It's actually based on my SFT Instruct finetune of Mistral 7B, the one used as the evaluator in MiniHF.

https://t.co/925urkZhut

It's then weight decayed over the tuning towards the base model weights along with a KL loss on the base model, this helps prevent mode collapse.

author:jd_pressman kind:tweet on:mistral-7b year:2023

cited on: mistral-7b

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.