IlyasMoutawwakil

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

efficient-attention-benchmark

Benchmarking PyTorch eager vs torch.nn.functional.scaled_dot_product_attention vs HazyResearch implementation

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

scikit-learn

scikit-learn: machine learning in Python

streamlit

Streamlit — A faster way to build and share data apps.

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

From-0-to-Research-Scientist-resources-guide

Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation.

DAVAR-Lab-OCR

OCR toolbox from Davar-Lab

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Dive-into-OCR-by-Paddle

“Dive Into OCR” is a textbook developed by the PaddleOCR community that integrates OCR theory and practice.

argilla

Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.

phytoplankton-challenge

Our winning solution for the phytoplankton prediction kaggle competition.

flash-attention

Fast and memory-efficient exact attention

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

benchmark

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

lit-gpt3

dramatron

Dramatron uses large language models to generate coherent scripts and screenplays.

kafka-tweetoscope

A project where we used Kafka to handle streams of data from the Twitter API.

IlyasMoutawwakil

README repository

fcc-back-end-development-and-apis

My 5 Node.js, Express.js and MongoDB projects that I've built as part of my freeCodeCamp assignment.

huggingface-course

Discovering HuggingFace 🤗 through their amazing course.

optimum

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

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

alphatensor

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️