An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A cat(1) clone with wings.

🌸 A command-line fuzzy finder

A parallel implementation of gzip for modern multi-processor, multi-core machines.

Official electron build of draw.io

OCR system for Arabic language that converts images of typed text to machine-encoded text.

Implementation of Nougat Neural Optical Understanding for Academic Documents

A Repo For Document AI

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

Jekyll Template - Mediumish

A minimal, responsive, and feature-rich Jekyll theme for technical writing.

A python module that wraps the pdftoppm utility to convert PDF to PIL Image object

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Start a server from the MLX library.

GPT4All: Chat with Local LLMs on Any Device

The official code repository for the second edition of the O'Reilly book Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play.

the AI-native open-source embedding database

🦜🔗 Build context-aware reasoning applications

LLM Chain for answering questions from documents with citations

Complete deep learning project developed in Full Stack Deep Learning, 2022 edition. Generated automatically from https://github.com/full-stack-deep-learning/fsdl-text-recognizer-2022

🦉 ML Experiments and Data Management with Git

Code for the Kaggle Ensembling Guide Article on MLWave

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning …

Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)

Fit interpretable models. Explain blackbox machine learning.

Rich-cli is a command line toolbox for fancy output in the terminal

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

A collection of pre-trained, state-of-the-art models in the ONNX format

A framework for detecting, highlighting and correcting grammatical errors on natural language text. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.