Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

DrishtiSharma
/
dolphin-mistral-dpo-ultrafeedback-binarized-preferences-kto_pair

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Files and versions Metrics Training metrics Community
dolphin-mistral-dpo-ultrafeedback-binarized-preferences-kto_pair / runs
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
DrishtiSharma's picture
DrishtiSharma
Training in progress, step 500
d9f60e6 verified about 1 year ago
  • Feb22_15-13-14_ac25d7a97b3d
    Training in progress, step 500 about 1 year ago