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
317b5ac
llama3-sudo-dpo-10epochs-forget10mixall-1sft-2lora-1e-5
/
adapter_config.json
Commit History
Training in progress, step 1000
2525b93
verified
QinLiuNLP
commited on
21 days ago
QinLiuNLP
commited on
