Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
☆1,618Nov 24, 2025Updated 10 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☆1,427Mar 3, 2024Updated 2 years ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,433May 20, 2026Updated 4 months ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,856Jun 17, 2025Updated last year
- Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Langu…☆356Jun 18, 2023Updated 3 years ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,755Jan 8, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [NIPS2023] RRHF & Wombat☆804Sep 22, 2023Updated 3 years ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,081Oct 5, 2026Updated last week
- Reference implementation for DPO (Direct Preference Optimization)☆2,916Aug 11, 2024Updated 2 years ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆844Jul 1, 2024Updated 2 years ago
- Train transformer language models with reinforcement learning.☆19,498Updated this week
- A modular RL library to fine-tune language models to human preferences☆2,396Mar 1, 2024Updated 2 years ago
- JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.☆1,155Mar 17, 2025Updated last year
- 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。☆1,222Feb 27, 2024Updated 2 years ago
- BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）☆8,268Oct 16, 2024Updated last year
- 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.
- Recipes to train reward model for RLHF.☆1,545Apr 24, 2025Updated last year
- RewardBench: the first evaluation tool for reward models.☆743Updated this week
- Example models using DeepSpeed☆6,847Sep 30, 2026Updated last week
- Instruction Tuning with GPT-4☆4,333Jun 11, 2023Updated 3 years ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆185Oct 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…☆2,787Dec 12, 2023Updated 2 years ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,152Jun 1, 2023Updated 3 years ago
- Open Academic Research on Improving LLaMA to SOTA LLM☆1,602Aug 30, 2023Updated 3 years ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆196Jan 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☆5,693Sep 23, 2026Updated 2 weeks ago
- A large-scale 7B pretraining language model developed by BaiChuan-Inc.☆5,647Jul 18, 2024Updated 2 years ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆961Feb 16, 2025Updated last year
- NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms☆421Mar 20, 2024Updated 2 years ago
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,776Aug 4, 2024Updated 2 years ago
- Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)☆2,904Mar 13, 2024Updated 2 years ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,837Updated this week
- An open-source, tool-augmented conversational language model from Fudan University☆12,264Sep 6, 2026Updated last month
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆2,019Aug 9, 2025Updated last year
- 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.
- 面向中文大模型价值观的评估与对齐研究☆560Jul 20, 2023Updated 3 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☆3,036Apr 14, 2024Updated 2 years ago
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,389Jul 25, 2023Updated 3 years ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,614Mar 27, 2023Updated 3 years ago
- ☆283Jan 6, 2025Updated last year
- Scalable toolkit for efficient model alignment☆852Oct 6, 2025Updated last year
- NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark☆588Jul 21, 2026Updated 2 months ago