Hugging Face's logo

sfulay
/
zephyr-7b-dpo-full-gpt_consistent-reward-scale-1-rpo

Safetensors
mistral
trl
dpo
alignment-handbook
Generated from Trainer
Model card Files Community
zephyr-7b-dpo-full-gpt_consistent-reward-scale-1-rpo / special_tokens_map.json

Commit History

Training in progress, step 100
242749d
verified

sfulay commited on