Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
sciarrilli
/
Llama-3.2-3B-DPO
like
0
Transformers
Safetensors
trl-lib/ultrafeedback_binarized
Generated from Trainer
trl
dpo
arxiv:
2305.18290
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Llama-3.2-3B-DPO
/
tokenizer.json
Commit History
Model save
356ff86
verified
sciarrilli
commited on
Mar 18, 2025