RLHFlow AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
7
Downloads 30D
21.2K
Total downloads
951.3K
Total likes
361
Gained 7D
4,906

Most downloaded

  1. 1ArmoRM-Llama3-8B-v0.1Sep 23, 202415.9K
  2. 2Llama3.1-8B-PRM-Deepseek-DataMay 10, 20254,084
  3. 3LLaMA3-iterative-DPO-finalOct 14, 2024295
  4. 4pair-preference-model-LLaMA3-8BOct 14, 2024281
  5. 5RewardModel-Mistral-7B-for-DPA-v1May 23, 2024199
  6. 6Llama3.1-8B-PRM-Mistral-DataNov 9, 2024131
  7. 7Llama3.1-8B-ORM-Mistral-DataNov 9, 202478

Fastest growing

  1. 1ArmoRM-Llama3-8B-v0.1+4,372 in 7D15.9K
  2. 2Llama3.1-8B-PRM-Deepseek-Data+448 in 7D4,084
  3. 3LLaMA3-iterative-DPO-final+41 in 7D295
  4. 4pair-preference-model-LLaMA3-8B+0 in 7D281

Recently updated

  1. 1Llama3.1-8B-PRM-Deepseek-DataMay 10, 20254,084
  2. 2Llama3.1-8B-PRM-Mistral-DataNov 9, 2024131
  3. 3Llama3.1-8B-ORM-Mistral-DataNov 9, 202478
  4. 4pair-preference-model-LLaMA3-8BOct 14, 2024281
  5. 5LLaMA3-iterative-DPO-finalOct 14, 2024295
  6. 6ArmoRM-Llama3-8B-v0.1Sep 23, 202415.9K
  7. 7RewardModel-Mistral-7B-for-DPA-v1May 23, 2024199

All models

All tracked models published by RLHFlow
ModelDL 30D7D
ArmoRM-Llama3-8B-v0.1rlhflow/armorm-llama3-8b-v0.116.3K+4,372
Llama3.1-8B-PRM-Deepseek-Datarlhflow/llama3.1-8b-prm-deepseek-data4,254+448
LLaMA3-iterative-DPO-finalrlhflow/llama3-iterative-dpo-final275+41
pair-preference-model-LLaMA3-8Brlhflow/pair-preference-model-llama3-8b265+0
RewardModel-Mistral-7B-for-DPA-v1rlhflow/rewardmodel-mistral-7b-for-dpa-v1198+14
Llama3.1-8B-PRM-Mistral-Datarlhflow/llama3.1-8b-prm-mistral-data138—
Llama3.1-8B-ORM-Mistral-Datarlhflow/llama3.1-8b-orm-mistral-data114+31