Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
☆1,601Nov 24, 2025Updated 6 months ago
Alternatives and similar repositories for safe-rlhf
Users that are interested in safe-rlhf are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Secrets of RLHF in Large Language Models Part I: PPO☆1,428Mar 3, 2024Updated 2 years ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,523May 15, 2026Updated last week
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,369Updated this week
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,841Jun 17, 2025Updated 11 months ago
- Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Langu…☆355Jun 18, 2023Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,748Jan 8, 2024Updated 2 years ago
- [NIPS2023] RRHF & Wombat☆806Sep 22, 2023Updated 2 years ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,890Aug 11, 2024Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆845Jul 1, 2024Updated last year
- Train transformer language models with reinforcement learning.☆18,411Updated this week
- JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.☆1,115Mar 17, 2025Updated last year
- A modular RL library to fine-tune language models to human preferences☆2,387Mar 1, 2024Updated 2 years ago
- Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。☆1,162Feb 27, 2024Updated 2 years ago
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,281Oct 16, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Recipes to train reward model for RLHF.☆1,531Apr 24, 2025Updated last year
- RewardBench: the first evaluation tool for reward models.☆715Feb 16, 2026Updated 3 months ago
- Example models using DeepSpeed☆6,820Updated this week
- Instruction Tuning with GPT-4☆4,336Jun 11, 2023Updated 2 years ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆181Oct 27, 2023Updated 2 years ago
- We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tunin…☆2,797Dec 12, 2023Updated 2 years ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,128Jun 1, 2023Updated 2 years ago
- Open Academic Research on Improving LLaMA to SOTA LLM☆1,606Aug 30, 2023Updated 2 years ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆193Jan 16, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Robust recipes to align language models with human and AI preferences☆5,602Apr 8, 2026Updated last month
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆954Feb 16, 2025Updated last year
- A large-scale 7B pretraining language model developed by BaiChuan-Inc.☆5,659Jul 18, 2024Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,337May 16, 2026Updated last week
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,773Aug 4, 2024Updated last year
- NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms☆409Mar 20, 2024Updated 2 years ago
- Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)☆2,842Mar 13, 2024Updated 2 years ago
- An open-source tool-augmented conversational language model from Fudan University☆12,121Jul 13, 2024Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,985Aug 9, 2025Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 面向中文大模型价值观的评估与对齐研究☆556Jul 20, 2023Updated 2 years ago
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,391Jul 25, 2023Updated 2 years ago
- Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集☆3,052Apr 14, 2024Updated 2 years ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,600Mar 27, 2023Updated 3 years ago
- ☆284Jan 6, 2025Updated last year
- Scalable toolkit for efficient model alignment☆854Oct 6, 2025Updated 7 months ago
- NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark☆562Dec 4, 2025Updated 5 months ago