Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
QinLiuNLP
/
llama3-sudo-dpo-10epochs-forget10mixall-1sft-2lora-1e-5
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-10epochs-forget10mixall-1sft-2lora-1e-5
Commit History
Model save
10d8a09
verified
QinLiuNLP
commited on
21 days ago
Training in progress, step 1250
317b5ac
verified
QinLiuNLP
commited on
21 days ago
Training in progress, step 1000
2525b93
verified
QinLiuNLP
commited on
21 days ago
initial commit
1ad785f
verified
QinLiuNLP
commited on
21 days ago