payelb
/

HHRLHF_TinyLlama-1.1B_aligned_with_baseline_RM

Model card Files Files and versions

HHRLHF_TinyLlama-1.1B_aligned_with_baseline_RM / adapter_model.safetensors

Commit History

Upload PPO-aligned TinyLlama-1.1B model using baseline reward model on HHRLHF

967a11c
verified

payelb commited on 19 days ago