Starred repositories
ArMATH: The Arabic Math Word Problem dataset. Accepted in LREC2022
DigitalPlat FreeDomain: Free Domain For Everyone
Ω ΩΨͺΨ¨Ψ© Ψ§ΩΩ ΩΨͺΨ¨Ψ§Ψͺ Ψ§ΩΨ₯Ψ³ΩΨ§Ω ΩΨ©
Metadata extraction and validation in scientific papers
This package calculates the Daicritization Error Rate (DER) and Word Error Rate (WER) of the Arabic language.
A Django database backend and tooling for Timescaledb.
Machine Learning Engineering Open Book
A reading list on LLM based Synthetic Data Generation π₯
A concise but complete full-attention transformer with a set of promising experimental features from various papers
A commenting system powered by GitHub Discussions. π¬ π
A starter template for Jekyll sites using the Chirpy theme.
The dataset and code for paper: TheoremQA: A Theorem-driven Question Answering dataset
A lightweight next-gen data explorer - Postgres, MySQL, SQLite, MongoDB, Redis, MariaDB, Elastic Search, and Clickhouse with Chat interface
Open-source, self-hosted note-taking tool built for quick capture. Markdown-native, lightweight, and fully yours.
A reactive notebook for Python β run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
Reconstruct Arabic sentences to be used in applications that don't support Arabic
A curated list of awesome things related to Django
Code for the paper "Language Models are Unsupervised Multitask Learners"
A framework for few-shot evaluation of language models.
Anthropic's educational courses
A list of Free Software network services and web applications which can be hosted on your own servers
A high-throughput and memory-efficient inference and serving engine for LLMs