Code for the paper Fine-Tuning Language Models from Human Preferences
☆1,393Jul 25, 2023Updated 2 years ago
Alternatives and similar repositories for lm-human-preferences
Users that are interested in lm-human-preferences are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for "Learning to summarize from human feedback"☆1,063Sep 5, 2023Updated 2 years ago
- A modular RL library to fine-tune language models to human preferences☆2,390Mar 1, 2024Updated 2 years ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,753Jan 8, 2024Updated 2 years ago
- Train transformer language models with reinforcement learning.☆18,735Updated this week
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,847Jun 17, 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.
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,408May 20, 2026Updated last month
- A (somewhat) minimal library for finetuning language models with PPO on human feedback.☆91Nov 23, 2022Updated 3 years ago
- ☆1,257Dec 11, 2022Updated 3 years ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,426Mar 3, 2024Updated 2 years ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,894Aug 11, 2024Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,756Updated this week
- Aligning pretrained language models with instruction data generated by themselves.☆4,603Mar 27, 2023Updated 3 years ago
- Example models using DeepSpeed☆6,831Updated this week
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆845Jul 1, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- RLHF implementation details of OAI's 2019 codebase☆197Jan 14, 2024Updated 2 years ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,145Jun 1, 2023Updated 3 years ago
- [NIPS2023] RRHF & Wombat☆806Sep 22, 2023Updated 2 years ago
- ☆1,566Updated this week
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,607Nov 24, 2025Updated 7 months ago
- Ongoing research training transformer models at scale☆16,951Updated this week
- Instruction Tuning with GPT-4☆4,332Jun 11, 2023Updated 3 years ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆21,369Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,447Mar 20, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- RewardBench: the first evaluation tool for reward models.☆725Feb 16, 2026Updated 4 months ago
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,863May 29, 2026Updated last month
- Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"☆6,533Updated this week
- A framework for few-shot evaluation of language models.☆13,205Jun 24, 2026Updated last week
- Expanding natural instructions☆1,045Dec 11, 2023Updated 2 years ago
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆211Jul 31, 2023Updated 2 years ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,257Aug 14, 2025Updated 10 months ago
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,248Jul 17, 2024Updated last year
- Robust recipes to align language models with human and AI preferences☆5,627May 26, 2026Updated last month
- 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.☆1,534Apr 24, 2025Updated last year
- Scalable toolkit for efficient model alignment☆848Oct 6, 2025Updated 9 months ago
- ☆284Jan 6, 2025Updated last year
- Fast and memory-efficient exact attention☆24,304Jun 29, 2026Updated last week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆42,655Updated this week
- Toolkit for creating, sharing and using natural language prompts.☆3,026Oct 23, 2023Updated 2 years ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆306Mar 1, 2023Updated 3 years ago