Build local voice agents with open-source models

HiKid - Your AI English Pal. A desktop app built with React and TypeScript, targeting children in non-English-speaking countries who want to practice English speaking and listening.

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

深入剖析大语言模型架构、原理到训练部署 | How LLM works, including Design, Architecture and Training details.

📄 适合中文的简历模板收集（LaTeX，HTML/JS and so on）由 @hoochanlon 维护

A Survey of Reinforcement Learning for Large Reasoning Models

👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

人人都能用英语

一人企业方法论

《一人企业方法论》第二版，也适合做其他副业（比如自媒体、电商、数字商品）的非技术人群。

Create Epic Math and Physics Animations & Study Notes From Text and Images.

A community-maintained Python framework for creating mathematical animations.

a-m-team's exploration in large language modeling

adds Sequence Parallelism into LLaMA-Factory

A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Fully open data curation for reasoning models

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A series of math-specific large language models of our Qwen2 series.

Train transformer language models with reinforcement learning.

Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers g…

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

本项目用于大模型数学解题能力方面的数据集合成，模型训练及评测，相关文章记录。