argilla / notux-8x7b-v1

Text Generation47B207164Updated Mar 4, 2024

Downloads

207

Likes

164

Last updated

Mar 4, 2024

License

apache-2.0

This model is a preference-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the argilla/ultrafeedback-binarized-preferences-cleaned dataset using DPO (Direct Preference Optimization).

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • tensorboard
  • mixtral
  • text-generation
  • dpo
  • rlaif

Technical specifications

Parameters47B
Librarytransformers
Languagesen, de, es, fr, it
Licenseapache-2.0