Making large AI models cheaper, faster and more accessible

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Run agents as production software.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Official inference framework for 1-bit LLMs

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

A modular graph-based Retrieval-Augmented Generation (RAG) system

Make Your Company Data Driven. Connect to any data source, easily visualize, dashboard and share your data.

SGLang is a high-performance serving framework for large language models and multimodal models.

Fully open reproduction of DeepSeek-R1

Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

DeepSeek Coder: Let the Code Write Itself

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Fully automatic censorship removal for language models

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

🌈Python3网络爬虫实战：淘宝、京东、网易云、B站、12306、抖音、笔趣阁、漫画小说下载、音乐电影下载等

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

open-source agentic AI data assistant for the next generation of AI + Data products.

WebUI extension for ControlNet

Datasets, Transforms and Models specific to Computer Vision

Toolkit for linearizing PDFs for LLM datasets/training

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Ongoing research training transformer models at scale

Open Machine Learning Compiler Framework