payelb
/

HHRLHF_TinyLlama-1.1B_aligned_with_MARS_RM

Model card Files Files and versions

HHRLHF_TinyLlama-1.1B_aligned_with_MARS_RM

Commit History

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

a75499e
verified

payelb commited on 16 days ago

Upload tokenizer for HHRLHF-MARS aligned TinyLlama model

893df32
verified

payelb commited on 16 days ago

initial commit

7b9e0bc
verified

payelb commited on 16 days ago