daixuancheng on Hugging Face: model downloads

daixuancheng has 144 tracked models, downloaded 1,744 times in the last 30 days and 10,796 times in total. daixuancheng Wrapped: the last 12 months.

Models by downloads in the last 30 days

1. daixuancheng/distill_1.5b_base_code_global_step_400 21 downloads, text generation
2. daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step240 21 downloads, text generation
3. daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step40 20 downloads, text generation
4. daixuancheng/distill_1.5b_base_code_global_step_200 20 downloads, text generation
5. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step200 20 downloads, text generation
6. daixuancheng/4-23_docker_rbs32_model-Coder_step15 20 downloads, text generation
7. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step100 20 downloads, text generation
8. daixuancheng/distill_1.5b_base_code_global_step_640 20 downloads, text generation
9. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step140 19 downloads, text generation
10. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step80 19 downloads, text generation
11. daixuancheng/distill_1.5b_base_code_global_step_500 19 downloads, text generation
12. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step180 19 downloads, text generation
13. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step120 19 downloads, text generation
14. daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step100 18 downloads, text generation
15. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step20 18 downloads, text generation
16. daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20 18 downloads, model
17. daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard 18 downloads, model
18. daixuancheng/sac_static0.4_constrainbyAdv_step40 18 downloads, text generation
19. daixuancheng/sac_static0.4_constrainbyAdv_step60 18 downloads, text generation
20. daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step140 18 downloads, text generation
21. daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL 18 downloads, model
22. daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4 18 downloads, model
23. daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36 18 downloads, model
24. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step40 18 downloads, text generation
25. daixuancheng/distill_1.5b_base_code_global_step_300 17 downloads, text generation
26. daixuancheng/sac_static0.4_constrainbyAdv_step200 17 downloads, text generation
27. daixuancheng/sac_static0.4_constrainbyAdv_step180 17 downloads, text generation
28. daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step140 17 downloads, text generation
29. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step60 17 downloads, text generation
30. daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL 17 downloads, model
31. daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step220 17 downloads, text generation
32. daixuancheng/sac_static0.4_constrainbyAdv_step20 17 downloads, text generation
33. daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step160 16 downloads, text generation
34. daixuancheng/sac_static0.4_constrainbyAdv_step80 16 downloads, text generation
35. daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step200 16 downloads, text generation
36. daixuancheng/distill_1.5b_base_code_global_step_600 16 downloads, text generation
37. daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10 15 downloads, model
38. daixuancheng/distill_1.5b_base_code_global_step_100 15 downloads, text generation
39. daixuancheng/rerun_qwen-math-7b_noSuffix_base_step240 14 downloads, text generation
40. daixuancheng/4b-0404-2k 14 downloads, model
41. daixuancheng/rerun_qwen-math-7b_noSuffix_base_step260 14 downloads, text generation
42. daixuancheng/rerun_qwen-math-7b_noSuffix_base_step200 13 downloads, text generation
43. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_crtic 13 downloads, text generation
44. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step160_crtic 12 downloads, text generation
45. daixuancheng/0418_17K_filtered_10K_reward0.5_4b_inst 12 downloads, model
46. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step100_actor 12 downloads, text generation
47. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step140_actor 12 downloads, text generation
48. daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step280 12 downloads, text generation
49. daixuancheng/sac_static0.4_constrainbyAdv_step120 12 downloads, text generation
50. daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_300 12 downloads, text generation
51. daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step200 12 downloads, text generation
52. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step100_crtic 12 downloads, text generation
53. daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step260 12 downloads, text generation
54. daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step9 12 downloads, model
55. daixuancheng/ppo_sac_static0.1_constrainbyadv_step-140_actor 12 downloads, text generation
56. daixuancheng/fix-entropy-1e-3_train_math_global_step_40 12 downloads, text generation
57. daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio 12 downloads, model
58. daixuancheng/sac_static0.4_constrainbyAdv_step140 12 downloads, text generation
59. daixuancheng/sac_static0.1_constrainbyAdv_step100 12 downloads, text generation
60. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step40_actor 11 downloads, text generation
61. daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step240 11 downloads, text generation
62. daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step240 11 downloads, text generation
63. daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step240 11 downloads, text generation
64. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step200_crtic 11 downloads, text generation
65. daixuancheng/ppo_sac_static0.1_constrainbyadv_step-160_actor 11 downloads, text generation
66. daixuancheng/4-24-30BA3B-s233-final 11 downloads, model
67. daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step39 11 downloads, model
68. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_actor 11 downloads, text generation
69. daixuancheng/sac_static0.1_constrainbyAdv_step140 11 downloads, text generation
70. daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_640 11 downloads, text generation
71. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step160_actor 11 downloads, text generation
72. daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step140 11 downloads, text generation
73. daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step260 11 downloads, text generation
74. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step200_actor 11 downloads, text generation
75. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_crtic 11 downloads, text generation
76. daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step99 11 downloads, model
77. daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step40 10 downloads, text generation
78. daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step280 10 downloads, text generation
79. daixuancheng/fix-entropy-1e-3_train_math_global_step_160 10 downloads, text generation
80. daixuancheng/distill_1.5b_base_code_global_step_680 10 downloads, text generation
81. daixuancheng/sac_static0.1_constrainbyAdv_step20 10 downloads, text generation
82. daixuancheng/sac_static0.4_constrainbyAdv_step160_bak 10 downloads, text generation
83. daixuancheng/rerun_sac-init0.1_qwen-math-7b_constrainbyAdv_step200 10 downloads, text generation
84. daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_680 10 downloads, text generation
85. daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step220 10 downloads, text generation
86. daixuancheng/rerun_sac-init0.4_qwen-math-7b_constrainbyAdv_step40 10 downloads, text generation
87. daixuancheng/sac_static0.1_constrainbyAdv_step40 10 downloads, text generation
88. daixuancheng/sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step40 10 downloads, text generation
89. daixuancheng/sac_static0.1_constrainbyAdv_step80 10 downloads, text generation
90. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_crtic 10 downloads, text generation
91. daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_actor 10 downloads, text generation
92. daixuancheng/sac_static0.1_constrainbyAdv_step160 10 downloads, text generation
93. daixuancheng/ppo_sac_static0.1_constrainbyadv_step-100_actor 9 downloads, text generation
94. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step180_crtic 9 downloads, text generation
95. daixuancheng/distill_1.5b_sac-init0.4_constrainbyAdv_global_step_660 9 downloads, text generation
96. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step40_crtic 9 downloads, text generation
97. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step140_crtic 9 downloads, text generation
98. daixuancheng/sac_static0.1_constrainbyAdv_step120 9 downloads, text generation
99. daixuancheng/sac_static0.1_constrainbyAdv_step180 9 downloads, text generation
100. daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_actor 9 downloads, text generation