Quantized using 200 samples of 8192 tokens from an RP-oriented PIPPA dataset. For purposes other than RP, use quantizations done on a more general dataset. Bagel, Mixtral Instruct, with extra spices. Give it a taste. Works with Alpaca prompt formats, though the Mistral format should also work. I started experimenting around seeing if I could improve or fix some of Bagel’s problems. Totally inspired by seeing how well Doctor-Shotgun’s Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss worked (which is a LimaRP tune on top of base Mixtral, and then merged with Mixtral Instruct) — I decided to try some merges of Bagel with Mixtral Instruct as a result. Somehow I ended up here, Bagel, Mixtral Instruct, a little bit of LimaRP, a little bit of Sao10K’s Sensualize. So far in my testing it’s working very well, and while it seems fairly unaligned on a lot of stuff, it’s maybe a little too aligned on a few specific things (which I think comes from Sensualize) — so that’s something to play with in the future, or maybe try to DPO out. I’ve been running (temp last) minP 0.1, dynatemp 0.5-4, rep pen 1.07, rep range 1024. I’ve been testing Alpaca style Instruction/Response, and Instruction/Input/Response…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: intervitens-archive
Теги: mixtral, mergekit, merge, endpoints_compatible
Лайков: 3 | Загрузок: 13
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
