MultiRL on Hugging Face: model downloads

MultiRL has 170 tracked models, downloaded 1,550 times in the last 30 days and 66,829 times in total. MultiRL Wrapped: the last 12 months.

Models by downloads in the last 30 days

  1. MultiRL/qwen3_1.7b_easy_rl_fixed_gamma_1 19 downloads, model
  2. MultiRL/qwen3_1.7b_sudoku_one_act_new 19 downloads, model
  3. MultiRL/qwen3_1.7b_rush_hour_one_move_4_9_epoch1 19 downloads, model
  4. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480 18 downloads, model
  5. MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198 18 downloads, model
  6. MultiRL/qwen3_1.7b_rush_hour_one_move_4_9_epoch2 18 downloads, model
  7. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_296 18 downloads, model
  8. MultiRL/qwen3_1.7b_rush_hour_one_move_sft 18 downloads, model
  9. MultiRL/qwen3_1.7b_rush_hour_one_move_final 18 downloads, model
  10. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_592 17 downloads, model
  11. MultiRL/qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_288 17 downloads, model
  12. MultiRL/qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124 17 downloads, model
  13. MultiRL/qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_6672 17 downloads, model
  14. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888 17 downloads, model
  15. MultiRL/qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_562 17 downloads, model
  16. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_21_30 17 downloads, model
  17. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1480 17 downloads, model
  18. MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792 17 downloads, model
  19. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only 17 downloads, model
  20. MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_594 17 downloads, model
  21. MultiRL/qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9 16 downloads, model
  22. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch1 16 downloads, model
  23. MultiRL/qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_96 16 downloads, model
  24. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184 16 downloads, model
  25. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch3 16 downloads, model
  26. MultiRL/qwen3_1.7b_rush_hour_multi_move_sft_new 16 downloads, model
  27. MultiRL/qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_3336 16 downloads, model
  28. MultiRL/qwen3_1.7b_rush_hour_multi_move_final 16 downloads, model
  29. MultiRL/qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1686 16 downloads, model
  30. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch2 15 downloads, model
  31. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is_epoch3 15 downloads, model
  32. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_batch_128 15 downloads, model
  33. MultiRL/qwen3_1.7b_sudoku_one_action_easy_11_20 15 downloads, model
  34. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is 15 downloads, model
  35. MultiRL/qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216 15 downloads, model
  36. MultiRL/qwen3_1.7b_sudoku_one_action_easy_11_20_epoch1 14 downloads, model
  37. MultiRL/qwen3_1.7b_new_sudoku_one_action_new_sft_lr_5e_6 14 downloads, model
  38. MultiRL/qwen3_1.7b_sudoku_one_action_easy_21_30_epoch2 14 downloads, model
  39. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_296 14 downloads, model
  40. MultiRL/qwen3_1.7b_rush_hour_one_move_4_9_epoch3 14 downloads, model
  41. MultiRL/qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3 14 downloads, model
  42. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_10_12 14 downloads, model
  43. MultiRL/qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_4432 14 downloads, model
  44. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch1 14 downloads, model
  45. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_new 14 downloads, model
  46. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_mask_only 14 downloads, model
  47. MultiRL/qwen3_1.7b_easy_rl_final_group_norm 14 downloads, model
  48. MultiRL/qwen3_1.7b_easy_rl_reinforce_ori 14 downloads, model
  49. MultiRL/qwen3_1.7b_rush_hour_one_move_4_9 13 downloads, model
  50. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98_ori_norm 13 downloads, model
  51. MultiRL/qwen3_1.7b_sudoku_one_action_easy_11_20_epoch2 13 downloads, model
  52. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_11_20 13 downloads, model
  53. MultiRL/qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_3324 13 downloads, model
  54. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776 13 downloads, model
  55. MultiRL/qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_5004 13 downloads, model
  56. MultiRL/qwen3_1.7b_sudoku_one_action_easy_21_30_epoch3 12 downloads, model
  57. MultiRL/qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_192 12 downloads, model
  58. MultiRL/qwen3_1.7b_one_act_easy_short 11 downloads, model
  59. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888 11 downloads, model
  60. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is 11 downloads, model
  61. MultiRL/qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396 11 downloads, model
  62. MultiRL/qwen3_1.7b_sudoku_one_action_easy_21_30_epoch1 11 downloads, model
  63. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_21_30_epoch2 11 downloads, model
  64. MultiRL/qwen3_1.7b_medium_rl_ours_adv_fixed_sequence_from_epoch_3 11 downloads, model
  65. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_short_4_9 10 downloads, model
  66. MultiRL/qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1184 10 downloads, model
  67. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis 10 downloads, model
  68. MultiRL/qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_1668 10 downloads, model
  69. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_10_12_epoch1 10 downloads, model
  70. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_epoch_3 10 downloads, model
  71. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_geo_ms_token_tis 10 downloads, model
  72. MultiRL/qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_1108 10 downloads, model
  73. MultiRL/qwen3_1.7b_easy_rl_ours_adv_fixed_no_norm 10 downloads, model
  74. MultiRL/qwen3_1.7b_sudoku_multi_action_sft_final 9 downloads, model
  75. MultiRL/qwen3_4b_easy_rl_new 9 downloads, model
  76. MultiRL/qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_2248 9 downloads, model
  77. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_10_12_epoch3 9 downloads, model
  78. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_10_12_epoch2 9 downloads, model
  79. MultiRL/qwen3_4b_sft_one_act 9 downloads, model
  80. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch1 9 downloads, model
  81. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_4_9_long_10_12_epoch1 8 downloads, model
  82. MultiRL/qwen3_1.7b_sudoku_multi_action_one_act_allow_21_30_epoch2 8 downloads, model
  83. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_epoch4 8 downloads, model
  84. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_4_9_long_10_12_epoch2 8 downloads, model
  85. MultiRL/qwen3_1.7b_rush_hour_one_move_sft_new 8 downloads, model
  86. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_new_epoch6 8 downloads, model
  87. MultiRL/qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch3 8 downloads, model
  88. MultiRL/qwen3_1.7b_base_C_easy_short_sft_lr_1e_6 8 downloads, model
  89. MultiRL/qwen3_1.7b_easy_rl_gspo 8 downloads, model
  90. MultiRL/qwen3_1.7b_sudoku_sft 8 downloads, model
  91. MultiRL/qwen3_1.7b_sft_final 8 downloads, model
  92. MultiRL/qwen3_1.7b_webshop_macro_action_epoch1 8 downloads, model
  93. MultiRL/qwen3_1.7b_easy_reinforce_test 8 downloads, model
  94. MultiRL/qwen3_1.7b_webshop_macro_action 7 downloads, model
  95. MultiRL/qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch2 7 downloads, model
  96. MultiRL/qwen3_1.7b_rush_hour_multi_move_4_9_epoch3 7 downloads, model
  97. MultiRL/qwen3_1.7b_webshop_atomic_action_epoch3 7 downloads, model
  98. MultiRL/qwen3_1.7b_easy_rl_old_adv_fixed 7 downloads, model
  99. MultiRL/qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_384 7 downloads, model
  100. MultiRL/qwen3_1.7b_easy_rl_reinforce_alpha_1 7 downloads, model