Loubna Ben Allal
loubnabenallalcontact@gmail.com
Welcome to my personal page! 🌸 I'm Loubna, a Machine Learning Engineer at Hugging Face. My work focuses on making large language models (LLMs) better at programming and generating synthetic data.
I'm a member of the core team behind BigCode, and I've worked on The Stack dataset,
the largest open dataset of source code, as well as the StarCoder and StarCoder2 family of models.
Recently, I started working on generating synthetic data at scale and released Cosmopedia dataset.
I hold the MVA master's degree from ENS Paris Saclay (Paris, France) and an engineering degree from École des Mines de Nancy, with a major in Mathematics (Nancy, France).
I'm based in Paris, but I grew up in Morocco, in a small town called Midelt.
Talks
- December 19th 2022, online talk about CodeParrot at a research seminar in KTH Royal Institute of Technology in Stockholm.
- February 9th, 2023, online talk about The Stack & Code LLMs fine-tuning at the department of innovation of the European Parliament.
- Febrary 22nd, 2023, webinar about BigCode Project and Code LLMs to MoroccoAI.Youtube Recording.
- May 5th, 2023, online presentation about SantaCoder paper at the Deep Learning For Code Workshop at ICLR.
- May 16th, 2023,webinar about StarCoder to MLOPS Learners. Youtube Recording
- June 21th, 2023, online presentation about StarCoder to Emirates Data Science department.
- August 17th, 2023, webinar to Analytics Vidhya. Slides.
- September 9th, 2023, in-person talk at DataFest Yerevan in Yerevan, Armenia. Youtube Recording - Slides.
- September 23rd, 2023, in-person talk about Building LLMs for Code at GOSIM Workshop in Shanghai, China. Youtube Recording - Slides.
- September 26th, 2023, in-person talk about Open and Responsible development of Code Models at GOSIM Conference in Shanghai, China. Youtube Recording.
- September 28th, 2023, in-person Keynote to 1500+ attendeed at KubeCon + CloudNativeCon + Open Source Summit China 2023. Youtube Recording - Slides.
- November 24th, 2023, online talk at Al Akhawayn University. Slides.
- October 16th, 2023, talk about Introduction to Machine Leaning for High School students (in French) at Teens in AI. Slides.
- February 12th, 2024, in-person talk about "Generative AI: LLMs & Beyond" at Sciences Po Slides.
- April 4th, 2024, in-person talk about "Overview of BigCode and the landscape of LLMs for Code" at Station F. Slides.
- April 9th, 2024, in-person talk about "The landscape of LLMs for Code and their adaptation to custom codebases" at Qcon London. Slides.