hugpadhugpad

anthracite-org / magnum-v2.5-12b-kto

Text Generation12B12858Updated Aug 22, 2024
Hugging Face

Downloads

128

Likes

58

Last updated

Aug 22, 2024

License

apache-2.0

v2.5 KTO is an experimental release; we are testing a hybrid reinforcement learning strategy of KTO + DPOP, using rejected data sampled from the original model as "rejected". For "chosen", we use data from the original finetuning dataset as "chosen". This was done on a limited…

Tasks & library

  • text generation

Tags

  • mistral
  • chat
  • text-generation
  • conversational
  • en
  • fr

Technical specifications

Parameters12B
LibraryNot available
Languages9 languages
Base modelanthracite-org/magnum-12b-v2
Licenseapache-2.0