《动手学大模型Dive into LLMs》系列编程实践教程

A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models"

A collection of paper/projects that trains flow matching model/policies via RL.

A summary of related works about flow matching, stochastic interpolants

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)

Renderer for the harmony response format to be used with gpt-oss

The Best Agent Harness. Meet Sisyphus: The Batteries-Included Agent that codes like you.

Universal Pasteboard Across Devices

Awesome List for Agentic RL

Official Project Page for Deep Delta Learning (https://huggingface.co/papers/2601.00417)

A Cookbook to start building with LLMs

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Interactive visualizations of the geometric intuition behind diffusion models.

An open-source AI agent that brings the power of Gemini directly into your terminal.

Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

Official implementation of "Continuous Autoregressive Language Models"

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/

Datasets, SOTA results of every fields of Chinese NLP

TorchCFM: a Conditional Flow Matching library

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

The best ChatGPT that $100 can buy.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

A trusty face analysis research platform developed by Tencent Youtu Lab

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.