Abu Bakr Soliman

mini-rag. An Educational Project (step by step) to teach how to build a production-ready app for RAG application.

mazinger. End-to-end video dubbing pipeline

aravec. AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding models.

fastapi-ignite. A production-ready FastAPI boilerplate application with a comprehensive set of features for modern web backend development.

rafah-support. An AI Digital Assistant Extension for Helping Customer Support Agents

multilingual-lists. Multilingual lists of countries names, capitals, phone codes and more in (<select>,<ul> and JSON) formats.

tweety. Readable LLMs Evaluations

khod.fekra. An automated twitter robot which built with Python + Selenium to crawl last online stores deals and tweet about them.

RapidFit. Turn a handful of labeled examples into a production-ready multi-task classifier.

Datasets.

temporal-101-course. Hands-on Python examples for learning Temporal IO through a small progression of projects:

rafah. Rafah NLP Annotation Tool

alternative-smolagents.

flask-elastic-microservice. A demo of how to design a Flask micro-service for ElasticSearch. It also demonstrate how to interact with external API service like IBM Watson

jabarti-llm-from-scratch. Python

ml-course. Machine Learning Course - Arabic

angular2. Angular2 Course Tuts Codes

xminers. Xminers.club Tutorials Notebooks

w-task-report. Jupyter Notebook

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

machine-learning-course-101.

sentence-transformers. State-of-the-Art Text Embeddings

whisply-updated. 💬 Transcribe, translate, diarize, annotate and subtitle video (and audio) with Whisper on Win, Linux and Mac ... fast!

TextRecognitionDataGenerator. A synthetic data generator for text recognition

lighteval. LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

AutoGPTQ. An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

deep-text-recognition-benchmark. Text recognition (optical character recognition) with deep learning methods.

news-please. news-please - an integrated web crawler and information extractor for news that just works