Daixuan Cheng's picture

Daixuan Cheng

daixuancheng

·

https://github.com/cdxeve

DaixuanC45443

AI & ML interests

None yet

Recent Activity

liked a model 13 days ago

zai-org/GLM-4.7

updated a model 17 days ago

daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL

published a model 17 days ago

daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL

View all activity

Organizations

None yet

daixuancheng 's models 136

daixuancheng/distill_1.5b_base_code_global_step_500

Text Generation • 2B • Updated Jun 24, 2025 • 4

daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step100

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step100

Text Generation • 8B • Updated Jun 24, 2025 • 5

daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_100

Text Generation • 2B • Updated Jun 24, 2025 • 4

daixuancheng/distill_1.5b_base_code_global_step_400

Text Generation • 2B • Updated Jun 24, 2025 • 4

daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step200

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step40

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/distill_1.5b_base_code_global_step_200

Text Generation • 2B • Updated Jun 24, 2025 • 4

daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step40

Text Generation • 8B • Updated Jun 24, 2025 • 5

daixuancheng/distill_1.5b_base_code_global_step_100

Text Generation • 2B • Updated Jun 24, 2025 • 4

daixuancheng/sac_static0.4_constrainbyAdv_step100

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step140

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-140_critic

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/rerun_qwen-math-7b_noSuffix_base_step140

Text Generation • 8B • Updated Jun 24, 2025 • 2

daixuancheng/rerun_qwen-math-7b_noSuffix_base_step200

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-140_actor

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/sac_static0.4_constrainbyAdv_step40

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step100_actor

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step100

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-100_critic

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/sac_static0.1_constrainbyAdv_step100

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/rerun_qwen-math-7b_noSuffix_base_step100

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/fix-entropy-1e-3_train_math_global_step_100

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/sac_static0.1_constrainbyAdv_step40

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step40

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/rerun_qwen-math-7b_noSuffix_base_step40

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/fix-entropy-1e-3_train_math_global_step_40

Text Generation • 8B • Updated Jun 24, 2025 • 3

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-100_actor

Text Generation • 8B • Updated Jun 24, 2025 • 2

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step40_actor

Text Generation • 8B • Updated Jun 24, 2025 • 4

daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_600

Text Generation • 2B • Updated Jun 24, 2025 • 3