Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
QinLiuNLP
/
llama3-sudo-dpo-3epochs-forget10mix400-1sft-2fullpara
like
0
TensorBoard
Safetensors
llama
trl
dpo
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
main
llama3-sudo-dpo-3epochs-forget10mix400-1sft-2fullpara
Commit History
Model save
16401cf
verified
Jackie999
commited on
Oct 6, 2024
Training in progress, step 75
d859795
verified
Jackie999
commited on
Oct 6, 2024
initial commit
5b73ae4
verified
Jackie999
commited on
Oct 6, 2024