# @jd_pressman — 2023-11-10

♥3 ↻0 · https://x.com/jd_pressman/status/1723117826507210938

@Dorialexander @RiversHaveWings Here's a simple HuggingFace format LoRa you can play with to get a sense of how a decent RL tune compares to Mistral base. In my experiments it gives more coherent dialogue than the base model, has more interesting takes on stuff, with no mode collapse.

https://t.co/YmmgWNv8Lc

tags: author:jd_pressman, kind:tweet, on:mistral-7b, year:2023
cited on: _dossiers/mistral-7b.md, mistral-7b