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.

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

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

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

Universal LLM Deployment Engine with ML Compilation

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

A school for camelids

Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting has…

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

Fast and memory-efficient exact attention

Visual Object Tracking algorithms. Hold on! There is a lot to come

[MIGRATED TO KRONOS] A webapp to serve past year records-grade distributions of IITKGP

Domain-specific BERT representation for Named Entity Recognition of lab protocol

The PyTorch codebase for the NAACL 2021 paper - "tWT–WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets"

Codebase accompanying the paper "Leveraging Event Specific and Chunk Span features to Extract COVID Events from tweets" - WNUT @ EMNLP 2020

NAACL 2022, What do tokens know about their characters and how do they know it?

The Pytorch code for baselines and dataset accompanying the NAACL 2021 paper - "tWT–WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets"