The Vesuvius Challenge is a machine learning and computer vision competition to read the Herculaneum Papyri.

Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

docTR by Mindee (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

视觉预训练基础模型仓库

Notes and links from the book club meetings

Porting steamcomparer to NuxtJS for SSR

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.

Ryan's contributions to the Comma.ai speed challenge

Contains my experiments to build a Zomato reviews' sentiment classifier

Library to scrape and clean web pages to create massive datasets.

Keras BERT with pre-trained weights

Mixed Effects Random Forest

Embed categorical variables via neural networks.

Simple script in order to visualize memory used by individual python variables and visualized windirstat style.

San Diego Machine Learning group's open work on the human protein atlas image classification challenge

The best way to write secure and reliable applications. Write nothing; deploy nowhere.

A collection of problems and solution to explore reinforcement learning

Deep Learning and Reinforcement Learning Library for Scientists and Engineers

starter from "How to Train a GAN?" at NIPS2016

Neural network plotting function used to graph and animate neural networks during the feed-forward pass