Making large AI models cheaper, faster and more accessible

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

Large Language-and-Vision Assistant built towards multimodal GPT-4 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.

[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

Creative interactive views of any dataset.

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

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

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

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

Emu: An Open Multimodal Generalist

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

Segment-anything related awesome extensions/projects/repos.

Code Base for MinD-Video

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

This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"

Sample to envision intelligent apps with Microsoft's Copilot stack for AI-infused product experiences.