hugpadhugpad

OpenAssistant / reward-model-deberta-v3-large

Other32325Updated Feb 17, 2023
Hugging Face

Downloads

323

Likes

25

Last updated

Feb 17, 2023

License

mit

Reward model (RM) trained to predict which generated answer is better judged by a human, given a question.

Tasks & library

  • text classification
  • transformers

Tags

  • transformers
  • pytorch
  • deberta-v2
  • text-classification
  • reward-model
  • reward_model

Technical specifications

ParametersNot available
Librarytransformers
Languagesen
Licensemit