Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Magpie-Align
/
Llama-3.1-8B-Magpie-Align-v0.2
like
2
Safetensors
Magpie-Align/Llama-3.1-70B-PO-100K-armorm
English
llama
alignment-handbook
trl
dpo
Generated from Trainer
arxiv:
2406.08464
arxiv:
2406.12845
License:
llama3.1
Model card
Files
Files and versions
Community
Train
main
Llama-3.1-8B-Magpie-Align-v0.2
/
eval_results.json
Commit History
End of training
f98f101
verified
flydust
commited on
Aug 3