🤗 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.

🦜🔗 The platform for reliable agents.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Robust Speech Recognition via Large-Scale Weak Supervision

Python tool for converting files and office documents to Markdown.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

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

A high-throughput and memory-efficient inference and serving engine for LLMs

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

Inference code for Llama models

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

⏬ Dumb downloader that scrapes the web

Grok open release

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

Making large AI models cheaper, faster and more accessible

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

TensorFlow code and pre-trained models for BERT

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

A generative speech model for daily dialogue.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

What the f*ck Python? 😱

Automatic SQL injection and database takeover tool

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Easily train a good VC model with voice data <= 10 mins!