Bharat Raghunathan's Projects
Tesseract Open Source OCR Engine (main repository)
All-in-one text de-duplication
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Graph Convolutional Networks for Text Classification. AAAI 2019
extract text from any document. no muss. no fuss.
Exploring Text Summarization Techniques
An open letter of gratitude to GitHub
Code Repository for The Kaggle Workbook, Published by Packt
A comprehensive reference for all topics related to Natural Language Processing
Collection of NLP model explanations and accompanying analysis tools
π₯Fast State-of-the-Art Tokenizers optimized for Research and Production
Pytorch domain library for recommendation systems
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
π€ Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
A quick recipe to learn all about Transformers
βοΈ CLI tool to run Twilio Functions locally for development
Twitter bot that posts the current status of our hackerspace
The official Umbraco Documentation
Build Mobile, Desktop and WebAssembly apps with C# and XAML. Today. Open source and professionally supported.
A Python vector database you just need - no more, no less.
Datasets, Transforms and Models specific to Computer Vision
PyTorch code for EMNLP 2020 Paper "Vokenization: Improving Language Understanding with Visual Supervision"
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
Visual Studio Code
Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder and WizardMath
XAI - An eXplainability toolbox for machine learning