Skip to content

MahmoudMohamed

Reward_Model

Based on OpenAssistant/reward-model-deberta-v3-base

Tags

  • tensorboard
  • safetensors
  • deberta-v2
  • trl
  • reward-trainer
  • generated_from_trainer
  • dataset:Anthropic/hh-rlhf
  • base_model:OpenAssistant/reward-model-deberta-v3-base
  • base_model:finetune:OpenAssistant/reward-model-deberta-v3-base
  • license:mit
  • text-embeddings-inference
  • endpoints_compatible
Author
MahmoudMohamed
Task
text-classification
Library
transformers
Architecture
deberta-v2
License
mit
Base model
OpenAssistant/reward-model-deberta-v3-base
Downloads
14
Likes
0
Reward_Model — AI Model — AIMarketly