Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

P2P terminal game about spacepirates playing basketball across the galaxy

A lightweight, terminal-based application to view and query delimiter separated value formatted documents, such as CSV or TSV files.

Your journal app if you live in a terminal

A feature-rich command-line audio/video downloader

SGLang is yet another fast serving framework for large language models and vision language models.

LVBench: An Extreme Long Video Understanding Benchmark

Python scraper based on AI

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Matryoshka Multimodal Models

GPT4V-level open-source multi-modal model based on Llama3-8B

Mixture-of-Experts for Large Vision-Language Models

MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts

MambaOut: Do We Really Need Mamba for Vision?

BY Blog ->

A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

Multimodal Models in Real World

Code for paper "Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning"

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

A series of large language models trained from scratch by developers @01-ai

Grok open release

ImageBind One Embedding Space to Bind Them All

The official implementation of "Relay Diffusion: Unifying diffusion process across resolutions for image synthesis" [ICLR 2024 Spotlight]

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

A curated list of reinforcement learning with human feedback resources (continually updated)

LongAlign: A Recipe for Long Context Alignment Encompassing Data, Training, and Evaluation

Scenic: A Jax Library for Computer Vision Research and Beyond

Reading list for research topics in multimodal machine learning