·
AI & ML interests
None yet
Organizations
ybenpan/single_turn_64_global_step40
33B • Updated
ybenpan/qwen3_single_turn_global_step80
33B • Updated
• 1
ybenpan/qwen3_max_reward_global_step40
33B • Updated
• 1
ybenpan/0328_overnight_grpo_16_global_step40
33B • Updated
• 7
ybenpan/qwen3_global_step44
33B • Updated
• 8
ybenpan/max_reward_gamma_0_8_parse_drgrpo_global_step94
33B • Updated
• 10
ybenpan/max_reward_gamma_0_8_parse_drgrpo_global_step40
33B • Updated
• 7
ybenpan/bs64_global_step29
33B • Updated
• 7
ybenpan/bs64_global_step18
33B • Updated
• 6
ybenpan/max_reward_gamma_0_4_global_step30
33B • Updated
• 9
ybenpan/max_reward_gamma_0_8_global_step39
33B • Updated
ybenpan/gamma_0_8_global_step60
33B • Updated
ybenpan/gamma_0_8_global_step40
33B • Updated
ybenpan/0327_overnight_global_step30
33B • Updated
• 1
ybenpan/0320_overnight_resume_kl_global_step40
33B • Updated
• 1
ybenpan/0320_overnight_resume2_global_step44
33B • Updated
• 1
ybenpan/0320_overnight_resume2_global_step45
33B • Updated
ybenpan/0320_overnight_global_step40
33B • Updated
• 1
ybenpan/0320_overnight_global_step36
33B • Updated
• 1
ybenpan/0320_overnight_global_step30
33B • Updated