arxiv:2410.01257
Alexander Bukharin
alexwb
·
AI & ML interests
None yet
Organizations
Papers
2
models
8
alexwb/reward_modeling_anthropic_hh_rm1e-3
Updated
•
4
alexwb/reward_modeling_anthropic_hh_rm1e-4
Updated
•
4
alexwb/reward_modeling_anthropic_hh_rm1.4e-5
Updated
•
6
alexwb/reward_modeling_anthropic_hh_rm1e-6
Updated
•
4
alexwb/reward_modeling_anthropic_hh_rm0.99
Updated
•
5
alexwb/reward_modeling_anthropic_hh_rm0.9_lr5e-5
Updated
•
4
alexwb/reward_modeling_anthropic_hh
Text Classification
•
Updated
•
6
alexwb/sft_trl_test
Updated
datasets
None public yet