daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step40 Text Generation • 8B • Updated 26 days ago • 5
daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step140 Text Generation • 8B • Updated 26 days ago • 8
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-140_critic Text Generation • 8B • Updated 26 days ago • 6
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-140_actor Text Generation • 8B • Updated 26 days ago • 5
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step100_actor Text Generation • 8B • Updated 26 days ago • 6
daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step100 Text Generation • 8B • Updated 26 days ago • 6
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-100_critic Text Generation • 8B • Updated 26 days ago • 6
daixuancheng/fix-entropy-1e-3_train_math_global_step_100 Text Generation • 8B • Updated 26 days ago • 5
daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step40 Text Generation • 8B • Updated 26 days ago • 5
daixuancheng/fix-entropy-1e-3_train_math_global_step_40 Text Generation • 8B • Updated 26 days ago • 5
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-100_actor Text Generation • 8B • Updated 26 days ago • 6
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step40_actor Text Generation • 8B • Updated 26 days ago • 5
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_600 Text Generation • 2B • Updated 26 days ago • 6
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_680 Text Generation • 2B • Updated 26 days ago • 7
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_660 Text Generation • 2B • Updated 26 days ago • 5
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_640 Text Generation • 2B • Updated 26 days ago • 6
daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_300 Text Generation • 2B • Updated 26 days ago • 5