Git Stars Git Stars

#reinforcement-learning-from-human-feedback Repositories

Discover 33 active open source GitHub repositories tagged with #reinforcement-learning-from-human-feedback, accumulating 86,497 total stars (averaging 2,621 stars per project). Leading this topic is huggingface/trl with 19,788 stars.

33
Total Repositories
86,497
Total Stars
2,621
Avg Stars/Repo
1
huggingface/trl

Train transformer language models with reinforcement learning.

huggingface
โญ 19,788 Python ๐Ÿ‘ค huggingface Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2020-03-27
2
OpenRLHF/OpenRLHF

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

OpenRLHF
โญ 10,173 Python ๐Ÿ‘ค OpenRLHF Organization ๐Ÿ• Updated 2026-11-03 ๐Ÿ“… Created 2023-07-30
3
zhaochenyang20/Awesome-ML-SYS-Tutorial

My learning notes for ML SYS.

zhaochenyang20
โญ 7,695 HTML ๐Ÿ‘ค zhaochenyang20 User ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2024-11-09
4
thinking-machines-lab/tinker-cookbook

Post-training with Tinker

thinking-machines-lab
โญ 4,291 Python ๐Ÿ‘ค thinking-machines-lab Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-07-14
5
allenai/open-instruct

AllenAI's post-training codebase

allenai
โญ 3,942 Python ๐Ÿ‘ค allenai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-06-09
6
deepseek-ai/DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

deepseek-ai
โญ 3,110 Python ๐Ÿ‘ค deepseek-ai Organization ๐Ÿ• Updated 2024-04-15 ๐Ÿ“… Created 2024-02-05
7
eric-mitchell/direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

eric-mitchell
โญ 2,826 Python ๐Ÿ‘ค eric-mitchell User ๐Ÿ• Updated 2024-08-11 ๐Ÿ“… Created 2023-06-22
8
Tencent-Hunyuan/HY-Motion-1.0

HY-Motion model for 3D human motion or 3D character animation generation.

Tencent-Hunyuan
โญ 2,679 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2025-12-29
9
yifan123/flow_grpo

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

yifan123
โญ 2,596 Python ๐Ÿ‘ค yifan123 User ๐Ÿ• Updated 2026-05-07 ๐Ÿ“… Created 2025-05-08
10
FoundationAgents/awesome-foundation-agents

About Awesome things towards foundation agents. Papers / Repos / Blogs / ...

FoundationAgents
โญ 2,200 ๐Ÿ‘ค FoundationAgents Organization ๐Ÿ• Updated 2025-07-28 ๐Ÿ“… Created 2025-03-24
11
LeapLabTHU/Absolute-Zero-Reasoner

Official Repository of Absolute Zero Reasoner

LeapLabTHU
โญ 1,893 Python ๐Ÿ‘ค LeapLabTHU User ๐Ÿ• Updated 2025-08-24 ๐Ÿ“… Created 2025-05-02
12
BytedTsinghua-SIA/DAPO

An Open-source RL System from ByteDance Seed and Tsinghua AIR

BytedTsinghua-SIA
โญ 1,814 Python ๐Ÿ‘ค BytedTsinghua-SIA Organization ๐Ÿ• Updated 2025-05-11 ๐Ÿ“… Created 2025-03-17
13
lsdefine/simple_GRPO

A very simple GRPO implement for reproducing r1-like LLM thinking.

lsdefine
โญ 1,719 Python ๐Ÿ‘ค lsdefine User ๐Ÿ• Updated 2025-11-21 ๐Ÿ“… Created 2025-02-10
14
JiuhaiChen/BLIP3o

Official implementation of BLIP3o-Series

JiuhaiChen
โญ 1,667 Python ๐Ÿ‘ค JiuhaiChen User ๐Ÿ• Updated 2025-11-29 ๐Ÿ“… Created 2025-04-23
15
XueZeyue/DanceGRPO

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

XueZeyue
โญ 1,654 Python ๐Ÿ‘ค XueZeyue User ๐Ÿ• Updated 2025-10-16 ๐Ÿ“… Created 2025-05-08
16
PKU-Alignment/safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

PKU-Alignment
โญ 1,624 Python ๐Ÿ‘ค PKU-Alignment Organization ๐Ÿ• Updated 2025-11-24 ๐Ÿ“… Created 2023-05-15
17
alibaba/Pai-Megatron-Patch

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

alibaba
โญ 1,601 Python ๐Ÿ‘ค alibaba Organization ๐Ÿ• Updated 2025-12-15 ๐Ÿ“… Created 2023-09-04
18
Osilly/Vision-R1

[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Visionโ€‘R1, a reasoning MLLM that leverages coldโ€‘start initialization and RL training to incentivize reasoning capability.

Osilly
โญ 1,558 Python ๐Ÿ‘ค Osilly User ๐Ÿ• Updated 2026-03-20 ๐Ÿ“… Created 2025-02-03
19
Duxiaoman-DI/XuanYuan

Xuanyuan: Duxiaoman Chinese Financial Dialogue Large Model

Duxiaoman-DI
โญ 1,323 Python ๐Ÿ‘ค Duxiaoman-DI Organization ๐Ÿ• Updated 2025-01-07 ๐Ÿ“… Created 2023-05-21
20
Tencent-Hunyuan/SRPO

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

Tencent-Hunyuan
โญ 1,278 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-05-11 ๐Ÿ“… Created 2025-09-09
21
henrywoo/chatllama

ChatLLaMA ๐Ÿ“ข Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT

henrywoo
โญ 1,200 Python ๐Ÿ‘ค henrywoo User ๐Ÿ• Updated 2026-10-08 ๐Ÿ“… Created 2023-02-27
23
Xwin-LM/Xwin-LM

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

Xwin-LM
โญ 1,041 Python ๐Ÿ‘ค Xwin-LM Organization ๐Ÿ• Updated 2024-05-31 ๐Ÿ“… Created 2023-09-11
24
OSU-NLP-Group/Mind2Web

[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents

OSU-NLP-Group
โญ 1,036 Jupyter Notebook ๐Ÿ‘ค OSU-NLP-Group Organization ๐Ÿ• Updated 2025-11-05 ๐Ÿ“… Created 2023-04-21
25
kebijuelun/Awesome-LLM-Learning

Learning Large Language Model (LLM๏ผ‰(ๅคง่ฏญ่จ€ๆจกๅž‹ๅญฆไน )

kebijuelun
โญ 984 TypeScript ๐Ÿ‘ค kebijuelun User ๐Ÿ• Updated 2026-01-05 ๐Ÿ“… Created 2023-08-06
26
mst272/LLM-Dojo

Lightweight LLM Post-training Framework, supports SFT, RLVR, On-Policy KD, Guide KD, and mixed training; implements single/multi-round Guide distillation, multi-teacher distillation, Reward mixed training, and automated data sharding๐Ÿ‘ฉโ€๐ŸŽ“๐Ÿ‘จโ€๐ŸŽ“

mst272
โญ 939 Python ๐Ÿ‘ค mst272 User ๐Ÿ• Updated 2026-03-08 ๐Ÿ“… Created 2024-01-23
27
tatsu-lab/alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

tatsu-lab
โญ 840 Python ๐Ÿ‘ค tatsu-lab Organization ๐Ÿ• Updated 2024-07-01 ๐Ÿ“… Created 2023-05-03
28
CodeGoat24/UnifiedReward

Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex

CodeGoat24
โญ 831 Python ๐Ÿ‘ค CodeGoat24 User ๐Ÿ• Updated 2026-06-18 ๐Ÿ“… Created 2025-03-04
30
General-Analysis/GA

An encyclopedia of jailbreaking techniques to make AI models safer.

General-Analysis
โญ 583 Jupyter Notebook ๐Ÿ‘ค General-Analysis Organization ๐Ÿ• Updated 2025-05-26 ๐Ÿ“… Created 2025-01-18
31
Fancy-MLLM/R1-Onevision

R1-onevision, a visual language model capable of deep CoT reasoning.

Fancy-MLLM
โญ 581 Python ๐Ÿ‘ค Fancy-MLLM User ๐Ÿ• Updated 2025-04-13 ๐Ÿ“… Created 2025-02-08
โญ 567 Python ๐Ÿ‘ค yuvalkirstain User ๐Ÿ• Updated 2024-12-21 ๐Ÿ“… Created 2023-04-30
33
teacherpeterpan/self-correction-llm-papers

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

teacherpeterpan
โญ 562 ๐Ÿ‘ค teacherpeterpan User ๐Ÿ• Updated 2024-10-28 ๐Ÿ“… Created 2023-08-04

Frequently Asked Questions

1

What is the most popular #reinforcement-learning-from-human-feedback repository on GitHub?

The top ranked open source #reinforcement-learning-from-human-feedback project on GitHub is huggingface/trl with 19,788 stars. Train transformer language models with reinforcement learning.

2

Which programming languages are most used in #reinforcement-learning-from-human-feedback repositories?

Among the top ranked #reinforcement-learning-from-human-feedback projects on GitHub, the most common programming languages are Python, Jupyter Notebook, HTML, TypeScript.

3

How is the #reinforcement-learning-from-human-feedback repository ranking calculated?

We track 33 active open source repositories tagged with #reinforcement-learning-from-human-feedback (500+ stars), totaling 86,497 stars with an average of 2,621 stars per repository. Rankings update daily from the GitHub API.