RLHFlow on Hugging Face: downloads and rankings

RLHFlow has 37 tracked models, downloaded 23,939 times in the last 30 days and 1,097,738 times in total; 88 datasets, downloaded 5,280 times in the last 30 days. RLHFlow Wrapped: the last 12 months.

Models by downloads in the last 30 days

1. RLHFlow/ArmoRM-Llama3-8B-v0.1 16.1K downloads, text classification
2. RLHFlow/Llama3.1-8B-PRM-Deepseek-Data 5.3K downloads, text generation
3. RLHFlow/LLaMA3-SFT-v2 557 downloads, text generation
4. RLHFlow/LLaMA3-SFT 461 downloads, text generation
5. RLHFlow/pair-preference-model-LLaMA3-8B 335 downloads, text generation
6. RLHFlow/LLaMA3-iterative-DPO-final 289 downloads, text generation
7. RLHFlow/Llama3.1-8B-PRM-Mistral-Data 170 downloads, text generation
8. RLHFlow/Llama3.1-8B-ORM-Mistral-Data 146 downloads, text generation
9. RLHFlow/RewardModel-Mistral-7B-for-DPA-v1 144 downloads, text classification
10. RLHFlow/Llama3-v2-iterative-DPO-iter3 75 downloads, text generation
11. RLHFlow/Llama3.1-8B-ORM-Deepseek-Data 42 downloads, text generation
12. RLHFlow/Qwen2.5-Math-7B-Zero-RAFTpp 26 downloads, text generation
13. RLHFlow/Decision-Tree-Reward-Llama-3.1-8B 26 downloads, text classification
14. RLHFlow/Llama3-SFT-v2.0-epoch2 25 downloads, text generation
15. RLHFlow/LLaMA3.2-3B-SFT 23 downloads, text generation
16. RLHFlow/DPA-v1-Mistral-7B 22 downloads, text generation
17. RLHFlow/Qwen2.5-7B-PPO-Zero 20 downloads, model
18. RLHFlow/Llama3-v2-iterative-DPO-iter1 20 downloads, text generation
19. RLHFlow/Qwen2.5-7B-DPO-Zero 19 downloads, model
20. RLHFlow/Llama3-v2-iterative-DPO-iter2 19 downloads, text generation
21. RLHFlow/LLaMA3.2-1B-SFT 18 downloads, text generation
22. RLHFlow/Llama3-SFT-v2.0-epoch3 18 downloads, text generation
23. RLHFlow/Decision-Tree-Reward-Gemma-2-27B 18 downloads, text classification
24. RLHFlow/Qwen2.5-7B-DPO 17 downloads, model
25. RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej 17 downloads, text generation
26. RLHFlow/Qwen2.5-7B-SFT 15 downloads, model
27. RLHFlow/Llama3-SFT-v2.0-epoch1 13 downloads, text generation
28. RLHFlow/Qwen2.5-7B-RAFT-Zero 13 downloads, model
29. RLHFlow/Qwen2.5-Math-7B-Reinforce-Ada-balance-hard 12 downloads, model
30. RLHFlow/Llama-3.2-3B-Instruct-Reinforce-Ada-balance-hard 10 downloads, model
31. RLHFlow/Qwen3-4B-Instruct-2507-Reinforce-Ada-balance-hard 9 downloads, model
32. RLHFlow/Qwen2.5-Math-7B-Reinforce-Ada-balance-easy 8 downloads, model
33. RLHFlow/Qwen2.5-Math-1-5B-Reinforce-Ada-balance-easy 7 downloads, model
34. RLHFlow/Qwen2.5-Math-1.5B-DAPO-easy 7 downloads, model
35. RLHFlow/Qwen2.5-Math-1-5B-Reinforce-Ada-balance-hard 6 downloads, model
36. RLHFlow/Qwen2.5-Math-1.5B-GRPO-n8-easy 6 downloads, model
37. RLHFlow/Qwen2.5-7B-DPO-NLL-Zero 3 downloads, model

Datasets by downloads in the last 30 days

1. RLHFlow/HH-RLHF-Helpful-standard 609 downloads
2. RLHFlow/UltraFeedback-preference-standard 549 downloads
3. RLHFlow/Helpsteer-preference-standard 269 downloads
4. RLHFlow/PKU-SafeRLHF-30K-standard 220 downloads
5. RLHFlow/prompt-collection-v0.1 218 downloads
6. RLHFlow/Argilla-Math-DPO-standard 205 downloads
7. RLHFlow/CodeUltraFeedback-standard 194 downloads
8. RLHFlow/UltraInteract-filtered-standard 193 downloads
9. RLHFlow/Capybara-distibalel-Filter-standard 193 downloads
10. RLHFlow/Orca-distibalel-standard 177 downloads
11. RLHFlow/RLHFlow-SFT-Dataset-ver2 166 downloads
12. RLHFlow/Prometheus2-preference-standard 138 downloads
13. RLHFlow/Deepseek-PRM-Data 118 downloads
14. RLHFlow/SHP-standard 103 downloads
15. RLHFlow/Mistral-PRM-Data 86 downloads
16. RLHFlow/pair_data_v2_80K_wsafety 78 downloads
17. RLHFlow/iterative-prompt-v1-iter1-20K 65 downloads
18. RLHFlow/pair-preference-dataset-mix1 58 downloads
19. RLHFlow/iterative-prompt-v1-iter2-20K 58 downloads
20. RLHFlow/SFT-OpenHermes-2.5-Standard 55 downloads
21. RLHFlow/Deepseek-MATH500-Test 53 downloads
22. RLHFlow/Deepseek-ORM-Data 49 downloads
23. RLHFlow/pair_preference_model_dataset 49 downloads
24. RLHFlow/Mistral-ORM-Data 47 downloads
25. RLHFlow/prm80k-phase2 46 downloads
26. RLHFlow/pair-preference-dataset-700K 44 downloads
27. RLHFlow/LLM-Preferences-HelpSteer2 44 downloads
28. RLHFlow/iterative-prompt-v1-iter3-20K 42 downloads
29. RLHFlow/reinforce_ada_hard_prompt 39 downloads
30. RLHFlow/HH-RLHF-Harmless-and-RedTeam-standard 39 downloads
31. RLHFlow/Deepseek-ORM-Data-Pairwise 39 downloads
32. RLHFlow/numia_prompt_dpo3 37 downloads
33. RLHFlow/self_rewarding_sft_prompt 36 downloads
34. RLHFlow/Mistral-MATH500-Test 33 downloads
35. RLHFlow/self_rewarding_ift_example_raw_data1 33 downloads
36. RLHFlow/pair_data_v2_80K_wsafety_short 31 downloads
37. RLHFlow/Mistral-GSM8K-Test 30 downloads
38. RLHFlow/qwq_gen_sft_15k 29 downloads
39. RLHFlow/Deepseek-GSM8K-Test 27 downloads
40. RLHFlow/self_rewarding_rl_prompt 27 downloads
41. RLHFlow/numia_prompt_dpo_test 27 downloads
42. RLHFlow/iterative-prompt-v1-iter6-20K 26 downloads
43. RLHFlow/iterative-prompt-v1-iter7-20K 26 downloads
44. RLHFlow/reinforce_ada_hard_prompt_1-5b 26 downloads
45. RLHFlow/self_rewarding_turn1_with_rewards_example 26 downloads
46. RLHFlow/DS-and-Mistral-PRM-Data 25 downloads
47. RLHFlow/reinforce_ada_hard_prompt_llama 24 downloads
48. RLHFlow/numia_prompt_ppo 24 downloads
49. RLHFlow/numia_prompt_dpo6 24 downloads
50. RLHFlow/ArmoRM-Multi-Objective-Data-v0.2 23 downloads

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.