Sangsang on Hugging Face: model downloads

Sangsang has 224 tracked models, downloaded 2,624 times in the last 30 days and 10,621 times in total. Sangsang Wrapped: the last 12 months.

Models by downloads in the last 30 days

  1. Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-LoRA 43 downloads, text generation
  2. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-16-pm-e3 34 downloads, text generation
  3. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-16-pm 33 downloads, text generation
  4. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-16-pm-e1 32 downloads, text generation
  5. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-64-pm-e1 31 downloads, text generation
  6. Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-LoRA 31 downloads, text generation
  7. Sangsang/thinksafe-1.7B-n1-ablation_R32_BZ64_Gen8 31 downloads, text generation
  8. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-64-pm 30 downloads, text generation
  9. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-32-ep3-pm 30 downloads, text generation
  10. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-e3 29 downloads, text generation
  11. Sangsang/qwen3-1.7B-star-1-1.7B-modified-32-pm 28 downloads, text generation
  12. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-16-pm-e2 28 downloads, text generation
  13. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-64-pm-e2 28 downloads, text generation
  14. Sangsang/qwen3-1.7B-star-1-41K-32-pm 27 downloads, text generation
  15. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-32-ep2-pm 27 downloads, text generation
  16. Sangsang/safepath_Qwen3-1.7B 27 downloads, text generation
  17. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-64-pm-e3 27 downloads, text generation
  18. Sangsang/grpo_Qwen3-1.7B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 26 downloads, text generation
  19. Sangsang/qwen3-1.7B-thinksafe-r1-1.5B-32-pm 26 downloads, text generation
  20. Sangsang/ThinkSafe-Qwen3-8B-Activation-LoRA 25 downloads, text generation
  21. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-e2 24 downloads, text generation
  22. Sangsang/qwen3-1.7B-star-1-32-pm 24 downloads, text generation
  23. Sangsang/ThinkSafe-Qwen3-8B-ICL-LoRA 22 downloads, text generation
  24. Sangsang/qwen3-8B-thinksafe-r1-7B-32-pm 21 downloads, text generation
  25. Sangsang/feedback_asymmetric_fixed_ema_DeepSeek-R1-Distill-Llama-8B_bw0p5_fw0p5_ema0p999_ep30 19 downloads, text generation
  26. Sangsang/Llama-3.1-8B-rkl_rkl-4130 19 downloads, text generation
  27. Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen3-14B_bw0p5_fw0p5_ema0p999_ep30 18 downloads, text generation
  28. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only 18 downloads, text generation
  29. Sangsang/grpo_DeepSeek-R1-Distill-Llama-8B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30 18 downloads, text generation
  30. Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-3ep-harmful_only 18 downloads, text generation
  31. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-64-pm-e1 17 downloads, text generation
  32. Sangsang/qwen3-8B-star-1-32-pm 17 downloads, text generation
  33. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-16-pm-e1 16 downloads, text generation
  34. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e2 16 downloads, text generation
  35. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-64-pm-e2 16 downloads, text generation
  36. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-64-pm-e3 16 downloads, text generation
  37. Sangsang/qwen3-8B-thinksafe-8B-n1-64-pm 16 downloads, text generation
  38. Sangsang/feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 16 downloads, text generation
  39. Sangsang/R1-14B-thinksafe-DeepSeek-14B-32-pm-3ep 15 downloads, text generation
  40. Sangsang/qwen3-8B-star-1-41K-32-pm 15 downloads, text generation
  41. Sangsang/CI-7B-Feedback-merged 15 downloads, text generation
  42. Sangsang/feedback_asymmetric_fixed_ema_Qwen2.5-7B-Instruct_bw0p5_fw0p5_ema0p999_ep30 15 downloads, text generation
  43. Sangsang/R1-8B-thinksafe-DeepSeek-8B-unfiltered-32-pm-3ep 15 downloads, text generation
  44. Sangsang/qwen3-8B-thinksafe-8B-n1-16-pm 15 downloads, text generation
  45. Sangsang/feedback_disallowed_ema_DeepSeek-R1-Distill-Llama-8B_reverse_kl_ema0p999_ep30 14 downloads, text generation
  46. Sangsang/DeepSeek-R1-Distill-Llama-8B_from_Distill-Qwen-32B 14 downloads, text generation
  47. Sangsang/qwen3-8B-thinksafe-Qwen-8B-unfiltered-raw-32-pm-3ep 14 downloads, text generation
  48. Sangsang/ContextRLDEMO-Qwen3-4B-Instruct-4096-ep3 14 downloads, text generation
  49. Sangsang/CI-7B-CI-RL-merged 13 downloads, text generation
  50. Sangsang/feedback_allowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 13 downloads, text generation
  51. Sangsang/ci-feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 13 downloads, text generation
  52. Sangsang/Qwen2.5-7B-Instruct-feedback 13 downloads, text generation
  53. Sangsang/feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 13 downloads, text generation
  54. Sangsang/feedback_asymmetric_fixed_ema_DeepSeek-R1-Distill-Qwen-7B_bw0p5_fw0p5_ema0p999_ep30 13 downloads, text generation
  55. Sangsang/ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3 13 downloads, text generation
  56. Sangsang/Qwen2.5-7B-Instruct-ci-rl 13 downloads, text generation
  57. Sangsang/qwen3-0.6B-thinksafe-0.6B-filtered-olmo-3.1-32B-32-pm 13 downloads, text generation
  58. Sangsang/qwen3-14B-thinksafe-Qwen-14B-32-pm-3ep 13 downloads, text generation
  59. Sangsang/ci-feedback_both_interp_Qwen2.5-7B-Instruct_from_Qwen2.5-7B-Instruct_jsd_b0p8_stw0p3_ep30 13 downloads, text generation
  60. Sangsang/qwen3-8B-thinksafe-8B-n1-32-ep3-pm 12 downloads, text generation
  61. Sangsang/R1-8B-thinksafe-DeepSeek-8B-unfiltered-raw-32-pm-3ep 12 downloads, text generation
  62. Sangsang/qwen3-32B-direct-refusal-32-pm-5ep 12 downloads, text generation
  63. Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-ablation-32-pm-3ep-harmful_only 12 downloads, text generation
  64. Sangsang/qwen3-8B-thinksafe-8B-n1-32-ep2-pm 12 downloads, text generation
  65. Sangsang/R1-1.5B-thinksafe-r1-1.5B-ablation-16-pm-e1 12 downloads, text generation
  66. Sangsang/R1-8B-thinksafe-r1-8B-ablation-64-pm-e1 12 downloads, text generation
  67. Sangsang/R1-8B-safepath-DeepSeek-8B-32-pm-3ep 12 downloads, text generation
  68. Sangsang/qwen3-8B-thinksafe-Qwen-8B-unfiltered-32-pm-3ep 12 downloads, text generation
  69. Sangsang/sdpo_Qwen3-4B_lora32_n2048_seed42_lr1e-05_mcl16384_full_voacb 12 downloads, text generation
  70. Sangsang/R1-7B-thinksafe-r1-7B-16-pm 12 downloads, text generation
  71. Sangsang/Olmo-3-7B-Instruct-SFT-GRPOPE_8_eps20 11 downloads, text generation
  72. Sangsang/DS_CT_20250811_N200_NH800_B2_LEN_PRIOR 11 downloads, text generation
  73. Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-64-pm 11 downloads, text generation
  74. Sangsang/R1-8B-thinksafe-r1-8B-filtered-llama-3.3-70B-32-pm 11 downloads, text generation
  75. Sangsang/R1-7B-thinksafe-r1-7B-32-ep3-pm 11 downloads, text generation
  76. Sangsang/ci-feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30 11 downloads, text generation
  77. Sangsang/qwen3-14B-safechain-32-pm-3ep 11 downloads, text generation
  78. Sangsang/qwen3-0.6B-thinksafe-qwen-0.6B-n5-refusal-math-20k-5-pm 11 downloads, text generation
  79. Sangsang/DeepSeek-R1-Distill-Qwen-7B_pm_ep5 11 downloads, model
  80. Sangsang/DS_CT_20250811_N0_NH1000_B2_LEN_PRIOR 11 downloads, text generation
  81. Sangsang/qwen3-8B-thinksafe-8B-filtered-olmo-3.1-32B-32-pm 11 downloads, text generation
  82. Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192 11 downloads, text generation
  83. Sangsang/safepath_Qwen3-4B 11 downloads, text generation
  84. Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-64-pm-e3 11 downloads, text generation
  85. Sangsang/R1-8B-thinksafe-r1-8B-64-pm 11 downloads, text generation
  86. Sangsang/DS_CT_20250811_LIN_1024_LOUT_4096_N100_NH100_B8_LEN_NAIVE 11 downloads, text generation
  87. Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only 11 downloads, text generation
  88. Sangsang/R1-7B-thinksafe-r1-7B-ablation-16-pm-e3 11 downloads, text generation
  89. Sangsang/qwen3-14B-star-1-32-pm 11 downloads, text generation
  90. Sangsang/qwen3-4B-thinksafe-4B-n1-16-pm 11 downloads, text generation
  91. Sangsang/qwen3-4B-thinksafe-4B-n1-64-pm 11 downloads, text generation
  92. Sangsang/DeepSeek-R1-Distill-Qwen-14B_pm_ep5 11 downloads, model
  93. Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-16-pm-e3 11 downloads, text generation
  94. Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-16-pm 11 downloads, text generation
  95. Sangsang/R1-8B-thinksafe-r1-8B-ablation-64-pm-e2 10 downloads, text generation
  96. Sangsang/R1-8B-thinksafe-r1-8B-32-ep2-pm 10 downloads, text generation
  97. Sangsang/R1-8B-thinksafe-r1-8B-ablation-16-pm-e3 10 downloads, text generation
  98. Sangsang/R1-8B-thinksafe-r1-8B-ablation-16-pm-e2 10 downloads, text generation
  99. Sangsang/R1-1.5B-thinksafe-r1-1.5B-32-ep3-pm 10 downloads, text generation
  100. Sangsang/R1-1.5B-thinksafe-r1-1.5B-ablation-16-pm-e2 10 downloads, text generation