hugpadhugpad

ContextualAI / Contextual_KTO_Mistral_PairRM

Text Generation7.2B7433Updated Apr 26, 2024
Hugging Face

Downloads

74

Likes

33

Last updated

Apr 26, 2024

License

apache-2.0

This repo contains the model and tokenizer checkpoints for: - model family <bmistralai/Mistral-7B-Instruct-v0.2</b - optimized with the loss <bKTO</b - aligned using the snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset - via 3 iterations of KTO on one epoch of each training partit…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • mistral
  • text-generation
  • human feedback
  • rlhf
  • preferences

Technical specifications

Parameters7.2B
Librarytransformers
Languagesen
Licenseapache-2.0