PKU-Alignment/beaver-7b-v3.0-reward

Reinforcement Learning·PKU-Alignment· 338

safe-rlhf Reinforcement Learning 6.6B params

The Beaver reward model is a preference model trained using the PKU-SafeRLHF dataset. It can play a role in the safe RLHF algorithm, helping the Beaver model become more helpful.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull PKU-Alignment/beaver-7b-v3.0-reward

Model details

Task

Reinforcement Learning

Provider

PKU-Alignment

Framework

safe-rlhf

Parameters

6.6B

Size

12 GB

Downloads

338

Paper

arXiv:2302.13971

Updated

2024-04-20

About PKU-Alignment/beaver-7b-v3.0-reward

The Beaver reward model is a preference model trained using the PKU-SafeRLHF dataset. It can play a role in the safe RLHF algorithm, helping the Beaver model become more helpful.

Related Reinforcement Learning

P HumanCompatibleAI/ppo-seals-CartPole-v0 Reinforcement Learning 48.5K 17 🤗 HF P HumanCompatibleAI/ppo-Pendulum-v1 Reinforcement Learning 41.8K 6 🤗 HF P PaulVialard/ppo-Huggy Reinforcement Learning 4.6K 🤗 HF V TianheWu/VisualQuality-R1-7B Reinforcement Learning ·8.3B params 4.0K 14 🤗 HF S Tesleum/shirdel-coder-9b-claude-fable-5 Reinforcement Learning 3.7K 3 🤗 HF S mradermacher/SpatialThinker-7B-i1-GGUF Reinforcement Learning 3.6K 1 🤗 HF

Browse all Reinforcement Learning models →