HanningZhang on Hugging Face: model downloads

HanningZhang has 205 tracked models, downloaded 2,073 times in the last 30 days and 11,241 times in total. HanningZhang Wrapped: the last 12 months.

Models by downloads in the last 30 days

  1. HanningZhang/PhysProver-7B 25 downloads, text generation
  2. HanningZhang/OpenGenAlign-Llama3.1-8B-PPO-Step20-Baseline 24 downloads, text generation
  3. HanningZhang/deepseek_only_conjecture_claude_deepseek_train_data_max1_5e-7_bs32_decay1e-6_2ep_ep1 24 downloads, text generation
  4. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-Step10 23 downloads, text generation
  5. HanningZhang/physicslean_kimina_claude_kimina_and_deepseek_all_v2_ep2 23 downloads, text generation
  6. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-KL-Step30 22 downloads, text generation
  7. HanningZhang/OpenGenAlign-Llama3.2-3B-PPO-Step20 22 downloads, text generation
  8. HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_all_ep2 22 downloads, text generation
  9. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-Step20 21 downloads, text generation
  10. HanningZhang/deepseek_v2_7b_sft_5e-6_bs32 21 downloads, text generation
  11. HanningZhang/Llama3-sft-more-corr-rr60k-3ep 21 downloads, text generation
  12. HanningZhang/physicslean_kimina_claude_kimina_and_deepseek_all_v2_ep1 20 downloads, text generation
  13. HanningZhang/deepseek-prm 20 downloads, text generation
  14. HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_one_sample_ep2 20 downloads, text generation
  15. HanningZhang/physlean_ds_prover_noapply_grpo_1e-6_bs256_step35 20 downloads, text generation
  16. HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_one_sample_ep1 20 downloads, text generation
  17. HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_one_sample_ep2 19 downloads, text generation
  18. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-KL-0002-Step20 19 downloads, text generation
  19. HanningZhang/OpenGenAlign-Llama3.2-3B-PPO-Step30 19 downloads, text generation
  20. HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_one_sample_ep1 19 downloads, text generation
  21. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-KL-Step20 19 downloads, text generation
  22. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-Step30 18 downloads, text generation
  23. HanningZhang/physicslean_kimina_train_gen_from_claude_and_grok_deepseek_all_ep1 18 downloads, text generation
  24. HanningZhang/OpenGenAlign-Llama3.2-3B-PPO-Step30-Baseline 18 downloads, text generation
  25. HanningZhang/Llama3-sft-less-corr-rr60k-3ep 17 downloads, text generation
  26. HanningZhang/OpenGenAlign-Qwen2.5-7B-PPO-KL_Cliphigher-Step20 17 downloads, text generation
  27. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter4 16 downloads, text generation
  28. HanningZhang/OpenGenAlign-Qwen2-7B-GRPO-Step20 16 downloads, text generation
  29. HanningZhang/Llama3.1-Math-PRM 16 downloads, text generation
  30. HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_all_ep2 16 downloads, text generation
  31. HanningZhang/Mistral-MetaMath-7b 15 downloads, text generation
  32. HanningZhang/deepseek_v2_7b_sft_5e-6_bs16_ep3 15 downloads, text generation
  33. HanningZhang/deepseek_v2_7b_sft_5e-6_bs16_ep2 15 downloads, text generation
  34. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher040_em-iter1 15 downloads, text generation
  35. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter8 15 downloads, text generation
  36. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter2 15 downloads, text generation
  37. HanningZhang/OpenGenAlign-Llama3.1-8B-PPO-Step20 15 downloads, text generation
  38. HanningZhang/Llama3-non-delete-4-ORM 15 downloads, text generation
  39. HanningZhang/Qwen_numina_iter6_new 15 downloads, text generation
  40. HanningZhang/Llama3-Numina100K-ORM 14 downloads, text generation
  41. HanningZhang/physicslean_kimina_train_gen_from_grok_deepseek_all_ep1 14 downloads, text generation
  42. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter8 14 downloads, text generation
  43. HanningZhang/Llama3-Numina850K-ORM 14 downloads, text generation
  44. HanningZhang/physlean_ds_prover_grpo_1e-6_bs256_step90 14 downloads, text generation
  45. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher050_em-iter3 14 downloads, text generation
  46. HanningZhang/Qwen-7B-grpo-plusplus-nocliphigher-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter7 14 downloads, text generation
  47. HanningZhang/Qwen_numina_iter7_new 14 downloads, text generation
  48. HanningZhang/Qwen_numina_iter3_new 14 downloads, text generation
  49. HanningZhang/MetaMath-7b 14 downloads, text generation
  50. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher040_em-iter3 13 downloads, text generation
  51. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher028_em-baseline_alldata_step30 13 downloads, text generation
  52. HanningZhang/Llama3-GSM8K-Star 13 downloads, text generation
  53. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter5 13 downloads, text generation
  54. HanningZhang/Llama3-sft-gsm8k-c2c50K-w2c48K-c100K-3ep 13 downloads, text generation
  55. HanningZhang/Qwen-7B-grpo-plusplus-nocliphigher-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter5 13 downloads, text generation
  56. HanningZhang/Qwen-7B-grpo-plusplus-nocliphigher-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter6 13 downloads, text generation
  57. HanningZhang/Qwen-7B-grpo-plusplus-nocliphigher-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter8 13 downloads, text generation
  58. HanningZhang/Llama3-Numina200K-ORM 13 downloads, text generation
  59. HanningZhang/Llama3-sft-more-corr-rr60k-2ep 13 downloads, text generation
  60. HanningZhang/Llama3-regular-balance-4-ORM 12 downloads, text generation
  61. HanningZhang/Distill_Qwen_1.5b_scalebio_rho 12 downloads, text generation
  62. HanningZhang/Distill_Qwen_1.5b_scalebio_ours 12 downloads, text generation
  63. HanningZhang/Llama3.1-RAG-Reward 12 downloads, text classification
  64. HanningZhang/Distill_Qwen_1.5b_scalebio_less 12 downloads, text generation
  65. HanningZhang/MathReward-7b 12 downloads, text generation
  66. HanningZhang/OpenGenAlign-Llama3.1-8B-GRPO-Step20 11 downloads, text generation
  67. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher028_em-baseline_alldata_step70 11 downloads, text generation
  68. HanningZhang/Qwen_dpo_no_nll_iter2 11 downloads, text generation
  69. HanningZhang/Llama3-GSM8K-w2c74.5K-c175K-c2c40K-2ep 11 downloads, text generation
  70. HanningZhang/Llama3-GSM8K-balance74.5K-c2c40K 11 downloads, text generation
  71. HanningZhang/scalebio-Qwen-rank-baseline 11 downloads, text generation
  72. HanningZhang/Llama3-sft-less-corr-rr60k-2ep 11 downloads, text generation
  73. HanningZhang/MetaMath-8b-3epoch 11 downloads, text generation
  74. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher040_then035_em-iter7 11 downloads, text generation
  75. HanningZhang/Llama3-w2r100k-r2r40k-r182k-3ep 11 downloads, text generation
  76. HanningZhang/goedel_v2_8b_sft_5e-6_bs32 11 downloads, text generation
  77. HanningZhang/dart-mistral-prm 11 downloads, text generation
  78. HanningZhang/Llama3-sft-gsm8k-c2c50K-w2c48K-c241K-2ep 11 downloads, text generation
  79. HanningZhang/Qwen2.5-Math-7B-grpo-plusplus_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter7 10 downloads, text generation
  80. HanningZhang/Llama3-w2r100k-r2r40k-r100k-3ep 10 downloads, text generation
  81. HanningZhang/Llama3-sft-gsm8k-c2c50K-w2c48K-c100K-2ep 10 downloads, text generation
  82. HanningZhang/Llama3-w2r100k-r2r40k-r100k-2ep 10 downloads, text generation
  83. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_cliphigher032_em-iter1 10 downloads, text generation
  84. HanningZhang/Llama3-sft-gsm8k-star-plus-2ep 10 downloads, text generation
  85. HanningZhang/Distill_Qwen_1.5b_scalebio_uniform 10 downloads, text generation
  86. HanningZhang/Llama3-w2r100k-r2r40k-r182k-2ep 10 downloads, text generation
  87. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter2 10 downloads, text generation
  88. HanningZhang/PRM-2e6-bz128-DS 10 downloads, text classification
  89. HanningZhang/Llama3-GSM8K-w2c74.5K-c175K-c2c40K 10 downloads, text generation
  90. HanningZhang/Qwen2.5-Math-7B-grpo-plusplus_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter4 10 downloads, text generation
  91. HanningZhang/Llama3-sft-more-corr-rr60k-orm 10 downloads, text generation
  92. HanningZhang/MathReward-13b 10 downloads, text generation
  93. HanningZhang/Qwen-7B-grpo-plusplus-nocliphigher-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter1 10 downloads, text generation
  94. HanningZhang/Qwen2.5-Math-7B-raft-plusplus_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter5 10 downloads, text generation
  95. HanningZhang/Qwen2.5-Math-7B-grpo-plusplus_em-sample1n8-sample8-filter1.0-insufficient0.0-a0.001-b2.0-iter5 10 downloads, text generation
  96. HanningZhang/Llama3-GSM8K-w2c74.5K-c175K-c2c40K-3ep 10 downloads, text generation
  97. HanningZhang/Llama3-GSM8K-w2c74.5K-c115K-c2c40K 10 downloads, text generation
  98. HanningZhang/Qwen_onlymath_iter9 10 downloads, text generation
  99. HanningZhang/Llama3-GSM8K-Noc2c 10 downloads, text generation
  100. HanningZhang/Llama3-sft-balanced-rr60k-orm 10 downloads, text generation