Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
QinLiuNLP
/
llama3-sudo-dpo-instruct-5epochs-forget10-1sft-2lora
like
0
PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
llama3-sudo-dpo-instruct-5epochs-forget10-1sft-2lora
/
runs
/
Oct03_22-23-52_COE-CS-sv002
1 contributor
History:
1 commit
Qin Liu
Training in progress, step 125
88640b4
verified
28 days ago
events.out.tfevents.1728019449.COE-CS-sv002.2062397.0
Safe
15.3 kB
LFS
Training in progress, step 125
28 days ago