Vik Paruchuri

zero_to_gpt. Go from no deep learning knowledge to implementing GPT.

texify. Math OCR model that outputs LaTeX and markdown

apartment-finder. A Slack bot that helps you find an apartment.

tabled. Detect and extract tables to markdown and csv

textbook_quality. Generate textbook-quality synthetic LLM pretraining data

libgen_to_txt. Convert all of libgen to high quality markdown

scribe. Simple speech recognition using your microphone.

researcher. Concise answers to search queries using Google and GPT-3. Includes citations.

triton_tutorial. Tutorials for Triton, a language for writing gpu kernels

classified. Score LLM pretraining data with classifiers

scan. Score essays automatically with an easy web interface.

evolve-music2. Evolve music automatically with python -- rewrite of evolve-music.

simpsons-scripts. Find out how much the simpsons characters like each other with text and audio analysis.

evolve-music. Superseded by github.com/vikparuchuri/evolve-music2 -- use that instead.

movide. The student-centric learning platform.

snapcheck. Find out if your info was leaked.

political-positions. Analyze politics.

vikparuchuri.com. Code for vikparuchuri.com -- personal blog.

pdf_to_md. Python

boston-python-ml. Text scoring/classification presentation

percept. A modular machine learning framework that is easy to test and deploy.

spotify-export. Export albums from Spotify into Google Play Music.

wp-deployment. Deploy wordpress with multisite to ec2 with ansible.

algorithms. Pure python implementations of various algorithms, including a matrix class.

gpt-fast. Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

olmocr. Toolkit for linearizing PDFs for LLM datasets/training

nyt-articles. Get articles from new york times API.

vikparuchuri-affirm. CSS

ds-webinar. How to learn data science webinar presentation

medicare-analysis. Analyze medicare data from the recent release.

streamlit-drawable-canvas. Do you like Quick, Draw? Well what if you could train/predict doodles drawn inside Streamlit? Also draws lines, circles and boxes over background images for annotation.

ml-math. Svelte

sports-stats. Try to rethink sports statistics.

TulaLensSurvey. Android app that makes it easy to survey people.

tmux-resurrect. Persists tmux environment across system restarts.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

bostonpython2015. Presentation for boston python 2015

dscontent-starter.

ray. Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

matter. Chrome extension that highlights important passages.

vj-wedding. Placeholder site for a wedding (with countdown)

openedx-scorm-xblock. SCORM XBlock for Open edX

vik-blog. HTML

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

nextml-talk. CSS

accelerate. 🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

tulalens-survey-web. Web component of android survey app.

openphi.

get-nytimes-articles. Python tools for getting data from the New York Times Article API. Retrieves JSON from the API, stores it, parses it into a CSV file.

contest. Python

vj-wedding2. A site I made for a wedding.

affirm-themes. Themes for affirm.io.