WPRM on Hugging Face: downloads and rankings

WPRM has 32 tracked models, downloaded 192 times in the last 30 days and 4,676 times in total; 119 datasets, downloaded 3,189 times in the last 30 days. WPRM Wrapped: the last 12 months.

Models by downloads in the last 30 days

1. WPRM/qwen-14b-text-policy-checkpoint-342 13 downloads, model
2. WPRM/qwenvl_bt_rm_wo_checklist 12 downloads, model
3. WPRM/qwen2.5-3b-rm-9k-5e-7-preference-sh 10 downloads, model
4. WPRM/qwen2.5-3b-rm-9k-5e-7-preference-sh-wo-checklist 10 downloads, model
5. WPRM/fa2_qwen2_5vl-3b_policy_bid_1e-5_bug_fixed_epoch3_adapter 9 downloads, model
6. WPRM/qwen2.5-3b-rm-scroll-filtered 8 downloads, model
7. WPRM/qwen2_5vl-3b_ar_reward_cot_multimodal 8 downloads, model
8. WPRM/qwen2.5-ar-reward-cot-final-new 7 downloads, model
9. WPRM/qwen2.5-ar-reward-cot-final 7 downloads, model
10. WPRM/qwen2.5-ar-reward-cot-mtl 7 downloads, model
11. WPRM/qwen3-8b-checklist-enhanced 7 downloads, model
12. WPRM/llama-3.1-policy-epoch1 7 downloads, model
13. WPRM/qwen2_5vl-3b_ar_reward_cot_multimodal_mtl 7 downloads, model
14. WPRM/qwen2.5-3b-rm-9k-5e-7-preference-sh-step50 7 downloads, model
15. WPRM/qwen2_5_text_3b_policy_bid_1e-5_unrepeated_16bit_merged 6 downloads, model
16. WPRM/RM-BT-no-CoT-v1-epoch1 6 downloads, model
17. WPRM/qwenvl_bt_rm 6 downloads, model
18. WPRM/policy-bid-text-epoch5-1e-5 5 downloads, model
19. WPRM/qwen-3b-ar-reward-cot-mtl-checklist-enhanced 4 downloads, model
20. WPRM/qwen3-8b-ar-reward-cot-mtl-checklist-enhanced 4 downloads, model
21. WPRM/qwen2_5vl-3b_ar_reward_cot_wo_checklist_multimodal 4 downloads, model
22. WPRM/qwen2.5-ar-reward-cot 4 downloads, model
23. WPRM/qwen2.5-ar-reward-cot-new 4 downloads, model
24. WPRM/llama-3.1-8b-ar-rm-mtl 4 downloads, model
25. WPRM/qwen2.5-ar-reward-no-cot 4 downloads, model
26. WPRM/fa2_qwen2_5vl-3b_policy_bid_1e-5_bug_fixed_adapter 4 downloads, model
27. WPRM/qwen2_7b_checklist_generation_1e-5_epoch_10_r16_checkpoint_156_merged 4 downloads, model
28. WPRM/llama-3.2-3b-policy 3 downloads, model
29. WPRM/fa2_qwen2_5_text_7b_policy_bid_1e-5_unrepeated_16bit_merged 3 downloads, model
30. WPRM/qwen2_5vl-3b_ar_reward_cot_multimodal_final_new 3 downloads, model
31. WPRM/qwen3-ar-reward-cot-mtl 3 downloads, model
32. WPRM/qwen2.5-ar-reward-rejected-action-ablation-1 2 downloads, model

Datasets by downloads in the last 30 days

1. WPRM/preference_data_llama_factory_wo_checklist 463 downloads
2. WPRM/minibench-multimodal-mind2web 376 downloads
3. WPRM/human_annotation_web_rm_version_1 278 downloads
4. WPRM/preference_data_llama_factory_corrected_format_text_only 163 downloads
5. WPRM/preference_data_llama_factory_corrected_format 147 downloads
6. WPRM/annotated_webarena_checklist 138 downloads
7. WPRM/thought_action_bid_only_version_3 107 downloads
8. WPRM/minibench-mind2web 97 downloads
9. WPRM/preference_data_sh_wo_checklist 63 downloads
10. WPRM/thought_action_bid_only_version_2 61 downloads
11. WPRM/thought_action_bid_only_version_1 54 downloads
12. WPRM/minibench-mm-mind2web 41 downloads
13. WPRM/judge_with_checklist_cot_multimodal_final_new_filtered_8k 40 downloads
14. WPRM/preference_data_llama_factory_len_8k 34 downloads
15. WPRM/preference_data_llama_factory 30 downloads
16. WPRM/preference_data_version_1_9_5k 26 downloads
17. WPRM/thought_action_bid_only_version_2_sharegpt 25 downloads
18. WPRM/preference_data_llama_factory_len_15k_text_with_urls 25 downloads
19. WPRM/preference_data_llama_factory_len_15k_text 25 downloads
20. WPRM/judge_with_checklist_cot_multimodal 23 downloads
21. WPRM/webprm-rejected-action-ablation-dataset-rejected-action-1 22 downloads
22. WPRM/preference_data_version_1_9_5k_wo_checklist 22 downloads
23. WPRM/mini_benchmark_webarena 19 downloads
24. WPRM/4omini_img_obs_annotated_walite_combined_checkist 19 downloads
25. WPRM/preference_data_openrlhf_with_checklist_filtered_scroll 18 downloads
26. WPRM/webprm-instruction-ablation-dataset-instruction-0.5 18 downloads
27. WPRM/checklist_dataset_sharegpt_for_offline_ppo_short 18 downloads
28. WPRM/judge_wo_checklist_cot_multimodal_filtered_8k 17 downloads
29. WPRM/judge_with_checklist_cot_multimodal_filtered_8k 17 downloads
30. WPRM/preference_data_sh 17 downloads
31. WPRM/judge_with_checklist_cot_multimodal_final_new 17 downloads
32. WPRM/webprm-instruction-ablation-dataset-instruction-0.75 17 downloads
33. WPRM/preference_data_llama_factory_len_15k 16 downloads
34. WPRM/thought_action_bid_only_version_3_unrepeated_text_only_sharegpt 16 downloads
35. WPRM/webarena_checklist_raw 16 downloads
36. WPRM/judge_with_checklist_cot_multimodal_final_filtered_8k 15 downloads
37. WPRM/ours_mtl3_ep1_annotated_walite_combined_checklist_new 15 downloads
38. WPRM/judge_with_checklist_cot_final_new 14 downloads
39. WPRM/evaluator-text-only-correct-and-incorrect 14 downloads
40. WPRM/checklist_with_reproduce_data 14 downloads
41. WPRM/qwen3b_annotated_walite_combined_checkist_new 14 downloads
42. WPRM/WebShepherd_train_text_only_final_same_ratio 14 downloads
43. WPRM/4omini_img_obs_annotated_walite_combined_checklist_login2 14 downloads
44. WPRM/ours_3b_mtl_enhanced_annotated_walite_combined_checklist 14 downloads
45. WPRM/preference_data_openrlhf_with_urls_len_8k 14 downloads
46. WPRM/preference_data_openrlhf_with_urls 13 downloads
47. WPRM/checklist_dataset_sharegpt_for_offline_ppo_tiny 13 downloads
48. WPRM/WebShepherd_train_text_only_final_0513 13 downloads
49. WPRM/evaluator-text-only-correct 12 downloads
50. WPRM/checklist_ours_mind2web-live 12 downloads