chchen
/

Llama-3.1-8B-Instruct-dpo-mistral-1000

Generated from Trainer

Model card Files Files and versions Community

Llama-3.1-8B-Instruct-dpo-mistral-1000 / training_rewards_accuracies.png

Commit History

End of training

1fbe65a
verified

chchen commited on May 19