payelb
/

PKUSafeRLHF_Llama-3.2-1B_aligned_with_MARS_deberta_RM

Model card Files Files and versions

PKUSafeRLHF_Llama-3.2-1B_aligned_with_MARS_deberta_RM / README.md

Commit History

Upload PPO-aligned Llama-3.2-1B model using MARS DeBERTa reward model on PKUSafeRLHF

9c4f7f8
verified

payelb commited on 12 days ago

Upload tokenizer for PKUSafeRLHF-MARS aligned Llama-3.2-1B model

6ba8a06
verified

payelb commited on 12 days ago