hugpadhugpad

argilla / CapybaraHermes-2.5-Mistral-7B

Other7.2B4973Updated Mar 4, 2024
Hugging Face

Downloads

49

Likes

73

Last updated

Mar 4, 2024

License

apache-2.0

This model is the launching partner of the capybara-dpo dataset build with ⚗️ distilabel. It's a preference tuned OpenHermes-2.5-Mistral-7B.

Tasks & library

  • trl

Tags

  • trl
  • mistral
  • distilabel
  • dpo
  • rlaif
  • rlhf

Technical specifications

Parameters7.2B
Librarytrl
Languagesen
Base modelteknium/OpenHermes-2.5-Mistral-7B
Licenseapache-2.0