vwxyzjn / lm-human-preference-detailsView external linksLinks
RLHF implementation details of OAI's 2019 codebase
☆197Jan 14, 2024Updated 2 years ago
Alternatives and similar repositories for lm-human-preference-details
Users that are interested in lm-human-preference-details are comparing it to the libraries listed below
Sorting:
- ☆160Nov 23, 2024Updated last year
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,377Jul 25, 2023Updated 2 years ago
- Secrets of RLHF in Large Language Models Part I: PPO☆1,416Mar 3, 2024Updated last year
- Language models scale reliably with over-training and on downstream tasks☆99Apr 2, 2024Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆842Jul 1, 2024Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆122Aug 22, 2024Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,742Jan 8, 2024Updated 2 years ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,853Aug 11, 2024Updated last year
- A modular RL library to fine-tune language models to human preferences☆2,377Mar 1, 2024Updated last year
- Code accompanying the paper Pretraining Language Models with Human Preferences☆180Feb 13, 2024Updated 2 years ago
- Train transformer language models with reinforcement learning.☆17,360Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)☆8,989Feb 6, 2026Updated last week
- Robust recipes to align language models with human and AI preferences☆5,495Sep 8, 2025Updated 5 months ago
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,296Dec 9, 2025Updated 2 months ago
- Recipes to train reward model for RLHF.☆1,514Apr 24, 2025Updated 9 months ago
- Scaling Data-Constrained Language Models☆340Jun 28, 2025Updated 7 months ago
- Official Code for M-RᴇᴡᴀʀᴅBᴇɴᴄʜ: Evaluating Reward Models in Multilingual Settings (ACL 2025 Main)☆40May 16, 2025Updated 9 months ago
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,582Nov 24, 2025Updated 2 months ago
- The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization☆918Mar 23, 2024Updated last year
- Minimalistic large language model 3D-parallelism training☆2,559Feb 11, 2026Updated last week
- Code and data for "KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark" (LREC-COLING…☆17Apr 15, 2025Updated 10 months ago
- ☆17Feb 19, 2024Updated last year
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Apr 20, 2024Updated last year
- AllenAI's post-training codebase☆3,573Feb 11, 2026Updated last week
- An Educational Framework Based on PyTorch for Deep Learning Education and Exploration☆10Dec 24, 2023Updated 2 years ago
- Exploring Model Kinship for Merging Large Language Models☆27Apr 16, 2025Updated 10 months ago
- ☆20Nov 4, 2025Updated 3 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,229Aug 14, 2025Updated 6 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆904Sep 30, 2025Updated 4 months ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,090Jun 1, 2023Updated 2 years ago
- Official repository for ORPO☆471May 31, 2024Updated last year
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆945Feb 16, 2025Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,946Aug 9, 2025Updated 6 months ago
- Notes on Direct Preference Optimization☆24Apr 14, 2024Updated last year
- RewardBench: the first evaluation tool for reward models.☆687Jan 31, 2026Updated 2 weeks ago
- Open-source Human Feedback Library☆11Oct 25, 2023Updated 2 years ago
- ☆25Aug 23, 2024Updated last year
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆211Jul 31, 2023Updated 2 years ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆588Dec 9, 2024Updated last year