Git Stars Git Stars

#post-training Repositories

Discover 17 active open source GitHub repositories tagged with #post-training, accumulating 20,413 total stars (averaging 1,200 stars per project). Leading this topic is hao-ai-lab/FastVideo with 4,833 stars.

17
Total Repositories
20,413
Total Stars
1,200
Avg Stars/Repo
Programming Languages: Python Jupyter Notebook
1
hao-ai-lab/FastVideo

A unified inference and post-training framework for accelerated video generation.

hao-ai-lab
โญ 4,833 Python ๐Ÿ‘ค hao-ai-lab Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-10-24
2
mbzuai-oryx/Awesome-LLM-Post-training

Awesome Reasoning LLM Tutorial/Survey/Guide

mbzuai-oryx
โญ 2,589 Python ๐Ÿ‘ค mbzuai-oryx Organization ๐Ÿ• Updated 2026-09-05 ๐Ÿ“… Created 2025-02-13
3
SmartFlowAI/EmoLLM

Mental Health Large Language Models (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

SmartFlowAI
โญ 1,797 Python ๐Ÿ‘ค SmartFlowAI Organization ๐Ÿ• Updated 2026-06-18 ๐Ÿ“… Created 2024-01-11
4
TokenRhythm/NeoHorse

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

TokenRhythm
โญ 1,708 Python ๐Ÿ‘ค TokenRhythm Organization ๐Ÿ• Updated 2026-09-26 ๐Ÿ“… Created 2026-09-04
5
worldbench/DiffusionOPSD

๐Ÿ”ฅ On-Policy Self-Distillation in Diffusion Models

worldbench
โญ 1,057 Python ๐Ÿ‘ค worldbench Organization ๐Ÿ• Updated 2026-10-12 ๐Ÿ“… Created 2026-07-29
6
AgileRL/AgileRL

The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

AgileRL
โญ 971 Python ๐Ÿ‘ค AgileRL Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-03-01
7
chrisliu298/awesome-on-policy-distillation

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

chrisliu298
โญ 926 ๐Ÿ‘ค chrisliu298 User ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2026-03-22
8
whitecircle/halo

Halo is an open-source framework built by White Circle for training large language and multimodal models

whitecircle
โญ 868 Python ๐Ÿ‘ค whitecircle Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-08-26
9
datawhalechina/llm-algo-leetcode

Hands-on LLM algorithms and systems with PyTorch, Triton & CUDA. โ€œLLM Algorithms and Systems Tutorialโ€: model architectures and training, post-training, inference acceleration, performance and operator optimization, with companion Notebook exercises, answer explanations, tests, and experiments.

datawhalechina
โญ 811 Jupyter Notebook ๐Ÿ‘ค datawhalechina Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-04-01
10
redai-studio/Relax

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

redai-studio
โญ 678 Python ๐Ÿ‘ค redai-studio Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-04-13
11
sunrainyg/RandOpt

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

sunrainyg
โญ 660 Python ๐Ÿ‘ค sunrainyg User ๐Ÿ• Updated 2026-09-21 ๐Ÿ“… Created 2026-02-18
12
aisa-group/PostTrainBench

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

aisa-group
โญ 627 Python ๐Ÿ‘ค aisa-group Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-11-28
13
turningpoint-ai/VisualThinker-R1-Zero

Explore the Multimodal โ€œAha Momentโ€ on 2B Model

turningpoint-ai
โญ 623 Python ๐Ÿ‘ค turningpoint-ai Organization ๐Ÿ• Updated 2025-03-18 ๐Ÿ“… Created 2025-02-24
14
HKUDS/LightReasoner

[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

HKUDS
โญ 616 Python ๐Ÿ‘ค HKUDS Organization ๐Ÿ• Updated 2026-05-22 ๐Ÿ“… Created 2025-09-29
15
fanegg/Human3R

[ICLR 2026] An unified model for 4D human-scene reconstruction

fanegg
โญ 569 Python ๐Ÿ‘ค fanegg User ๐Ÿ• Updated 2025-12-30 ๐Ÿ“… Created 2025-10-07
16
Gen-Verse/ReasonFlux

[NeurIPS 2025 Spotlight] LLM post-training suite โ€” featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

Gen-Verse
โญ 543 Python ๐Ÿ‘ค Gen-Verse Organization ๐Ÿ• Updated 2025-09-27 ๐Ÿ“… Created 2025-02-10
17
OpenDriveLab/WorldEngine

WorldEngine: Towards the Era of Post-Training for Autonomous Driving

OpenDriveLab
โญ 542 Python ๐Ÿ‘ค OpenDriveLab Organization ๐Ÿ• Updated 2026-11-05 ๐Ÿ“… Created 2026-04-08

Frequently Asked Questions

1

What is the most popular #post-training repository on GitHub?

The top ranked open source #post-training project on GitHub is hao-ai-lab/FastVideo with 4,833 stars. A unified inference and post-training framework for accelerated video generation.

2

Which programming languages are most used in #post-training repositories?

Among the top ranked #post-training projects on GitHub, the most common programming languages are Python, Jupyter Notebook.

3

How is the #post-training repository ranking calculated?

We track 17 active open source repositories tagged with #post-training (500+ stars), totaling 20,413 stars with an average of 1,200 stars per repository. Rankings update daily from the GitHub API.