hugpadhugpad

wzhouad / zephyr-7B-WPO-HB

Text Generation7.2B80Updated Aug 21, 2024
Hugging Face

Downloads

8

Likes

0

Last updated

Aug 21, 2024

License

Not available

mistral-7b-sft-beta model finetuned by hybrid WPO (GPT-4-turbo + on-policy sampling + Ultrafeedback). Details in WPO: Enhancing RLHF with Weighted Preference Optimization. The training data is wzhouad/zephyr-ultrafeedback-hybrid.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • mistral
  • text-generation
  • conversational

Technical specifications

Parameters7.2B
Librarytransformers
LanguagesNot available
LicenseNot available