Making large AI models cheaper, faster and more accessible

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

[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

[VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

EVA Series: Visual Representation Fantasies from BAAI

Images to inference with no labeling (use foundation models to train supervised models)

Creative interactive views of any dataset.

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

[MICCAI 2019] [MEDIA 2020] Models Genesis

InternVideo: General Video Foundation Models via Generative and Discriminative Learning (https://arxiv.org/abs/2212.03191)

Emu: An Open Multimodal Generalist

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.

Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena