payelb
/

UltraFeedback_openbmb_Llama-3.2-1B_aligned_with_MARS_deberta_RM

Model card Files Files and versions

UltraFeedback_openbmb_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 UltraFeedback_openbmb

410bbb9
verified

payelb commited on 12 days ago

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

4320694
verified

payelb commited on 12 days ago