sanduntg
/

output

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Commit History

sanduntg/llama_2_dpo_with_reward_1000

27e25fd
verified

sanduntg commited on Mar 20

sanduntg/llama_2_dpo_with_reward_2

38aaf25
verified

sanduntg commited on Mar 15

initial commit

5c2e62f
verified

sanduntg commited on Mar 15