ReactiveThings

llm.c

LLM training in simple, raw C/CUDA

proposal-signals

A proposal to add signals to JavaScript.

awesome-lego-machine-learning

A curated list of resources dedicated to Machine Learning applications to LEGO bricks

Document-AI

supervision

We write your reusable computer vision tools. 💜

jscpd

Copy/paste detector for programming source code.

linak-controller

A Python script to control Linak standing desks.

textra

A command-line application to convert images, PDFs, and audio files to text using Apple's APIs

LiLT

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

edit-distance-js

JavaScript library to compute the edit distance for strings and trees.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

tsgm

Generation and evaluation of synthetic time series datasets (also, augmentations, visualizations, a collection of popular datasets)

system-design-101

Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

slides

Terminal based presentation tool

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

long_llama

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

postgresml

The GPU-powered AI application database. Get your app to market faster using the simplicity of SQL and the latest NLP, ML + LLM models.

LLM-Agent-Paper-List

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

pix2struct

information_extraction

TypeChat

TypeChat is a library that makes it easy to build natural language interfaces using types.

SlideVQA

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)

deepdoctection

A Repo For Document AI

unilm

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

donut

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

llama2_aided_tesseract

Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections, complete with options for text validation and hallucination filtering.

OCR-Form-Tools

A set of tools to use in Microsoft Azure Form Recognizer and OCR services.