Gemma open-weight LLM library, from Google DeepMind

Building blocks for productive research

Inference script for Oasis 500M

realtime latent world model inference demo

Scalable metrics logging and analysis

Fast format for datasets

Fast and reliable distributed systems in Python

[train + eval + deploy] Aurora Series: A more efficient multimodal large language model series for video.

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

General Modules for JAX

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

The official repository of "Video assistant towards large language model makes everything easy"

Doing simple retrieval from LLM models at various context lengths to measure accuracy

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Tools and Utils for Experiments (TUX). Modified from many others' code to fit my needs.

Official repository for LongChat and LongEval

Easily create large video dataset from video urls

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Ongoing research training transformer models at scale