QinLiuNLP
/

llama3-sudo-dpo-5epochs-forget10mixall-1sft-2fullpara-1e-5

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

llama3-sudo-dpo-5epochs-forget10mixall-1sft-2fullpara-1e-5 / tokenizer.json

Commit History

Training in progress, step 625

d048d65
verified

QinLiuNLP commited on 6 days ago