Hugging Face's logo

DrishtiSharma
/
dolphin-2.1-mistral-7b-dpo-ultrafeedback-binarized-preferences-sigmoid

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Metrics Community
dolphin-2.1-mistral-7b-dpo-ultrafeedback-binarized-preferences-sigmoid / runs /Feb22_15-19-47_a1a9d1cfe150
  • 1 contributor
 History: 6 commits
DrishtiSharma's picture
DrishtiSharma
End of training
686f43a verified