AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Stable Diffusion web UI

Robust Speech Recognition via Large-Scale Weak Supervision

Animation engine for explanatory math videos

The official gpt4free repository | various collection of powerful language models

A natural language interface for computers

A Gradio web UI for Large Language Models.

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

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

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

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

⚡ A Fast, Extensible Progress Bar for Python and CLI

You like pytorch? You like micrograd? You love tinygrad! ❤️

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

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

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

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

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Inference code for CodeLlama models

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

DSPy: The framework for programming—not prompting—foundation models

Convert PDF to markdown quickly with high accuracy

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Mamba SSM architecture

Generate 3D objects conditioned on text or images

Gorilla: An API store for LLMs