Name: Wissam Antoun
Type: User
Company: Inria-ALMAnaCH
Bio: Research Engineer at INRIA,
prev. Data Scientist at SIREN,
prev. researcher at AUB MIND Lab.
Interested in AI and NLP, Tech and DIY projects
Twitter: wissam_antoun
Location: Paris-France
Blog: https://wissamantoun.github.io/
Wissam Antoun's Projects
An AIO Git repo of all algorithm competition source code for future reference.
Arabic NLP app built on streamlit to showcase models
AraELECTRA powered Arabic Wikipedia Question Answering system with Streamlit
This repository contains copies of the major repositories that contain Arabic QA dataset that follows the SQuAD format
Simple Pet feeder Controlled via SMS
Automatically exported from code.google.com/p/atmine
Robot Guided by an Android App, Computer Vision and Arduino
TensorFlow code and pre-trained models for BERT
Code for training CamemBERTa, a French language model based on DeBERTa V3. Development is done here https://gitlab.inria.fr/almanach/CamemBERTa
A microstrip patch antenna with circularly polarized matched to 50 Ω and operating at 2.4 GHz. SImulation done on HFSS
A small collection of CUDA Kernels
Giant Language Model Test Room
Visualize and explore NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2).
Simple Script to undo Farasa Segmentation, compatible with AraBERT pre-segmentation
A Python implementation of Farasa toolkit
Transformer related optimization, including BERT, GPT
Train Dense Passage Retriever (DPR) with a single GPU
Python example project used for a github actions tutorial
Create UIs for your machine learning model in Python in 3 minutes
:mag: End-to-end Python framework for building natural language search interfaces to data. Leverages Transformers and the State-of-the-Art of NLP. Supports DPR, Elasticsearch, Hugging Face’s Hub, and much more!
Code completion VSCode extension for OSS models
hULMonA (حلمنا): tHe first Universal Language MOdel iN Arabic