XuHuang/inpo_iter1
Updated
Xu Huang
XuHuang
AI & ML interests
None yet
Organizations
None yet
models
41
XuHuang/gemma-2-9b-it_mnpo_stage_2_athene_beta1_ratio0.85_eta0.005_weights0.75-0.25
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_1_athene_beta1_ratio0.33_eta0.005
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_2_skywork_beta3_ratio0.85_eta0.01_weights1-0_3pl_fixed
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_2_skywork_ratio0.85_eta0.01
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_1_skywork_inpo_iter1_20k
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_3_armo_beta5_ratio0.33_eta0.0075_weights0.25-0.75_td
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_2_armo_beta1_ratio0.8_eta0.005_weights0.75-0.25_3pl
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_2_armo_puredpoloss
606k
•
Updated
XuHuang/gemma-2-9b-it_mnpo_stage_2_armo_puredpoloss_beta5
606k
•
Updated