Loubna Ben Allal
where else to find them
website:https://loubnabnl.github.io/
github:loubnabnl
bluesky:loubnabnl.hf.co
linkedin:loubna-ben-allal-238690152
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
never shared a talk
who talks about the same things
- Andrés Marafioti2 talks
- Meriem Bendris2 talks
- Carton2 talks
- Jacek Golebiowski2 talks
- John Davies6 talks
- Joinal Ahmed6 talks
| title | conference | date |
|---|---|---|
| SmolLM: The Rise of Smol Models | Uphill Conf 2025 | 2025-04-24 |
Claims that compact models match much larger ones by training choices and data curation: SmolLM family has 100M, 300M, 1.7B variants, pretraining mixes curated… | ||
| Interview with Loubna Ben Allal | Uphill Conf 2025 | 2025-04-24 |
Describes building small LMs for phones that trade accuracy for much lower inference cost, outlines experiments on training and runtime efficiency, and… | ||
| Keynote: Pre-training and Fine-tuning of Code Generation Models | KubeCon + CloudNativeCon + Open Source Summit China 2023 | 2023-09-26 |
A 15B code model called StarCoder trains on permissive‑license GitHub plus issues, commits and notebooks with deduplication, decontamination and PII removal… | ||
| nothing matches | ||