siamakzd

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

keras

Deep Learning for humans

tesseract

Tesseract Open Source OCR Engine (main repository)

tuning_playbook

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

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

datasets

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

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

SEAL

Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

doctr

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

pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

awesome-document-understanding

A curated list of resources for Document Understanding (DU) topic

hlb-CIFAR10

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

concrete

Concrete: TFHE Compiler that converts python programs into FHE equivalent

data-centric-ai

Resources for Data Centric AI

concrete-ml

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

meerkat

Creative interactive views of any dataset.

TenSEAL

A library for doing homomorphic encryption operations on tensors

hlb-gpt

Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to larger models with one parameter change (feature currently in alpha).

mint

MinT: Minimal Transformer Library and Tutorials

FlexNeuART

Flexible classic and NeurAl Retrieval Toolkit

bros

xtreme-distil-transformers

XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale

minilmv2.bb

Our open source implementation of MiniLMv2 (https://aclanthology.org/2021.findings-acl.188)