Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
AIR-hl
/
Llama-3.2-3B-DPO
like
2
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
llama
trl
dpo
alignment
custome
chat
conversational
text-generation-inference
License:
llama3.2
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
2e57fb9
Llama-3.2-3B-DPO
/
runs
/
Jan05_19-50-22_notebook-7f74bd20-8f92-45b0-96c4-687ced4ee944
/
events.out.tfevents.1736078126.notebook-7f74bd20-8f92-45b0-96c4-687ced4ee944.3896.0
Commit History
upload
535e5d6
verified
AIR-hl
commited on
Jan 5
