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.

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

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Universal memory layer for AI Agents

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

结巴中文分词

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

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

Code and documentation to train Stanford's Alpaca models, and generate the data.

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

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Fast and memory-efficient exact attention

Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.

Train your AI self, amplify you, bridge the world

Python Implementation of Reinforcement Learning: An Introduction

A framework for few-shot evaluation of language models.

Source code for Twitter's Recommendation Algorithm

Python bindings for llama.cpp

Ollama Python library

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Accessible large language models via k-bit quantization for PyTorch.

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

Tools for merging pretrained large language models.

s1: Simple test-time scaling

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.