VikParuchuri

marker

Convert PDF to markdown quickly with high accuracy

surya

OCR, layout analysis, reading order, table recognition in 90+ languages

apartment-finder

A Slack bot that helps you find an apartment.

zero_to_gpt

Go from no deep learning knowledge to implementing GPT.

texify

Math OCR model that outputs LaTeX and markdown

tabled

Detect and extract tables to markdown and csv

textbook_quality

Generate textbook-quality synthetic LLM pretraining data

pdftext

Extract structured text from pdfs quickly

libgen_to_txt

Convert all of libgen to high quality markdown

researcher

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

classified

Score LLM pretraining data with classifiers

pdf_to_md

triton_tutorial

Tutorials for Triton, a language for writing gpu kernels

nyt-articles

Get articles from new york times API.

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

gpt-fast

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

openedx-scorm-xblock

SCORM XBlock for Open edX

openphi

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

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.

vllm

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

accelerate

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

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

bitsandbytes

8-bit CUDA functions for PyTorch

edx_xblock_scorm

XBlock to display SCORM content within the Open edX LMS. Editable within Open edx Studio. Will save student state and report scores to the progress tab of the course. Currently supports SCORM 1.2 and SCORM 2004 standard.

flash-attention

Fast and memory-efficient exact attention

optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

triton

Development repository for the Triton language and compiler