UCLA-AGI / Mistral7B-PairRM-SPPO-Iter1

Text Generation7.2B862Updated May 6, 2024

Downloads

86

Likes

2

Last updated

May 6, 2024

License

apache-2.0

Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675)

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • mistral
  • text-generation
  • conversational
  • en

Technical specifications

Parameters7.2B
Librarytransformers
Languagesen
Licenseapache-2.0