argilla / notus-7b-v1-lora-adapter

Text Generation03Updated Dec 4, 2023

Downloads

0

Likes

3

Last updated

Dec 4, 2023

License

mit

Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques. This model is the first version, fine-tuned with DPO over zephyr-7b-sft-full, which is the SFT model produced to create zephyr-7b-beta.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • dpo
  • preference
  • ultrafeedback
  • lora
  • text-generation

Technical specifications

ParametersNot available
Librarytransformers
Languagesen
Licensemit