MMLForge Search models, datasets, tasks… Start free
Home › Models › Safe Rlhf

Safe Rlhf Models

8

8 safe-rlhf models on MLForge, ranked by downloads — including work from PKU-Alignment. Compare, download and run them locally on your own GPU. Free tier.

Start freeDesktop app

Top Safe Rlhf models

B PKU-Alignment/beaver-7b-v1.0-cost Reinforcement Learning ·6.6B params 3.1K 10 🤗 HF B PKU-Alignment/beaver-7b-v1.0-reward Reinforcement Learning ·6.6B params 2.8K 17 🤗 HF B PKU-Alignment/beaver-7b-v3.0 Reinforcement Learning ·6.7B params 398 🤗 HF B PKU-Alignment/beaver-7b-v3.0-reward Reinforcement Learning ·6.6B params 338 🤗 HF B PKU-Alignment/beaver-7b-unified-cost Reinforcement Learning ·6.6B params 213 2 🤗 HF B PKU-Alignment/beaver-7b-v1.0 Reinforcement Learning ·6.7B params 135 13 🤗 HF B PKU-Alignment/beaver-7b-v3.0-cost Reinforcement Learning ·12.9B params 71 🤗 HF B PKU-Alignment/beaver-7b-unified-reward Reinforcement Learning ·6.6B params 32 🤗 HF

Other frameworks

Transformers 5659Diffusers 479Timm 341Ultralytics 225Transformers.Js 212Open Clip 209Sentence Transformers 197Pytorch 154Mlx 107PaddleOCR 97Ml Agents 93Stable Baselines3 90Peft 51Gguf 48Segmentation Models Pytorch 45Ggml 42Diffusion Single File 39Nemo 37Yolov5 36Mlx Audio 34