Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
QinLiuNLP
/
llama3-sudo-dpo-5epochs-forget10mix400-1sft-2fullpara-1e-5
like
0
TensorBoard
Safetensors
llama
trl
dpo
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
main
llama3-sudo-dpo-5epochs-forget10mix400-1sft-2fullpara-1e-5
/
config.json
Commit History
Training in progress, step 125
5e904b9
verified
QinLiuNLP
commited on
24 days ago
QinLiuNLP
commited on
