Hugging Face's logo

payelb
/
HHRLHF_Llama-3.2-1B_aligned_with_MARS_deberta_RM

PyTorch
Safetensors
Model card Files
xet
 Community
HHRLHF_Llama-3.2-1B_aligned_with_MARS_deberta_RM / adapter_model.safetensors

Commit History

Upload PPO-aligned Llama-3.2-1B model using MARS DeBERTa reward model on HHRLHF
176c1b6
verified

payelb commited on