tensorboy

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

HoT

[CVPR 2024 🔥] Official implementation of the paper "⏳ Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation"

Awesome_Long_Form_Video_Understanding

Awesome papers & datasets specifically focused on long-term videos.

langchain-extract

🦜⛏️ Did you say you like data?

LLaVA-PruMerge

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models

OpenDevin

🐚 OpenDevin: Code Less, Make More

AnyGPT

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

Graphzila

Turns text descriptions into detailed knowledge graphs, powered by OpenAI's GPT-3.5 Turbo. Customize node and edge attributes like colors and Wikipedia links to visualize information in an engaging way.

nvidia-tao

GraphGPT

Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

TinyLLaVA_Factory

A Framework of Small-scale Large Multimodal Models

RAR

The official implementation of RAR

KBQA-BERT

基于知识图谱的问答系统，BERT做命名实体识别和句子相似度，分为online和outline模式

Awesome-Embodied-AI

TextGrapher

Text Content Grapher based on keyinfo extraction by NLP method。输入一篇文档，将文档进行关键信息提取，进行结构化，并最终组织成图谱组织形式，形成对文章语义信息的图谱化展示。

MoneyPrinterTurbo

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

facexformer

Official implementation of FaceXFormer: A Unified Transformer for Facial Analysis

quiet-star

Code for Quiet-STaR

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

01

The open-source language model computer

mind-elixir-core

⚗ Mind Elixir is a JavaScript, framework-agnostic mind map core.

docusaurus

Easy to maintain open source documentation websites.

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

COCOPeriph

Official Repository for COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery ICLR 2024

lida

Automatic Generation of Visualizations and Infographics using Large Language Models

mindgraph

proof of concept prototype for generating and querying against an ever-expanding knowledge graph with ai

VL-Mamba

Implementation of "VL-Mamba: Exploring State Space Models for Multimodal Learning"

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

Agent-FLAN

[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

GLEE

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale