hugpadhugpad

mlabonne / AlphaMonarch-7B

Text Generation7.2B8.7K148Updated Mar 28, 2024
Hugging Face

Downloads

8.7K

Likes

148

Last updated

Mar 28, 2024

License

cc-by-nc-4.0

tl;dr: AlphaMonarch-7B is a new DPO merge that retains all the reasoning abilities of the very best merges and significantly improves its conversational abilities. Kind of the best of both worlds in a 7B model. 🎉

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • mistral
  • text-generation
  • merge
  • lazymergekit
  • dpo

Technical specifications

Parameters7.2B
Librarytransformers
Languagesen
Base modelmlabonne/NeuralMonarch-7B
Licensecc-by-nc-4.0