🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A general fine-tuning kit geared toward diffusion models.

A machine learning software for extracting information from scholarly documents

CLIP-like model evaluation

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。

A generative world for general-purpose robotics & embodied AI learning.

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Get your documents ready for gen AI

Kimi K2 is the large language model series developed by Moonshot AI team

Native Multimodal Models are World Learners

12 Lessons to Get Started Building AI Agents

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

[TMLR 2025🔥] A survey for the autoregressive models in vision.

Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

A lightweight, powerful framework for multi-agent workflows

Toolkit for linearizing PDFs for LLM datasets/training

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

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

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

DeepEP: an efficient expert-parallel communication library

🚀 Efficient implementations of state-of-the-art linear attention models

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