Virginie Lucienne
banner
webophage.bsky.social
Virginie Lucienne
@webophage.bsky.social
Reposted by Virginie Lucienne
We are excited to announce our next seminar by Fabian Suchanek (Télécom Paris, Institut Polytechnique de Paris) "On Language Models and Knowledge Bases" on Friday 21st November, 11am CET. Details can be found here: almanach.inria.fr/seminars-en....
November 7, 2025 at 3:47 PM
Reposted by Virginie Lucienne
Bonjourrrr
November 21, 2025 at 8:41 AM
Reposted by Virginie Lucienne
Les infections invasives à #méningocoques ont été très nombreuses ces dernières années et un rappel de vaccin (en dose unique) est recommandé aux ados de 11 ans à 14 ans.

D'où cette campagne organisée au collège 👇🏻

2/2

❗️ Attention, nouvelles règles ! La vaccination contre les infections à #méningocoques chez les enfants devient particulièrement difficile à suivre, à force d'être élargie. 🤯

On vous explique tout, avec évidemment une infographie ⤵️ @leparisien.fr

1/13

www.leparisien.fr/so...
November 13, 2025 at 10:44 AM
Reposted by Virginie Lucienne
@inriaparisnlp.bsky.social brought you CamemBERT, and we now bring you Gaperon (for non-cheese connoisseurs, it’s a cheese that’s flavoured with pepper and garlic 🧀 ).
We are proud to announce that we trained 1.5B, 8B, and 24B generative language models from scratch on 2 to 4 tera-tokens of carefully curated, high-quality data covering French, English and code. We release our models and code under open-source licences. Thread👇
November 12, 2025 at 11:18 PM
Reposted by Virginie Lucienne
Models (OpenRAIL-M licence): huggingface.co/collections/...
Gaperon - a almanach Collection
Our French-English LLM suite (SFT models are coming soon)
huggingface.co
November 12, 2025 at 5:26 PM
Reposted by Virginie Lucienne
I'm proud to share that at @inriaparisnlp.bsky.social we have released Gaperon — a suite of generative language models trained on French, English and code data, the largest of which has 24 billion parameters. Both the models and the code are being published under open licences. Short thread🧵
We are proud to announce that we trained 1.5B, 8B, and 24B generative language models from scratch on 2 to 4 tera-tokens of carefully curated, high-quality data covering French, English and code. We release our models and code under open-source licences. Thread👇
November 12, 2025 at 5:26 PM
Reposted by Virginie Lucienne
Our 24B base model seems particularly better than its open counterparts at generating text in generic contexts such as short stories or news articles, both in French and English
November 7, 2025 at 9:11 PM
Reposted by Virginie Lucienne
Yeah, posting something that big for us 2mn before the we in the US and late in the evening in France is so not ideal right before a 4 day week-end here, lol so we'll redo it again and tell you guys much more.. #TrainingTragedy
Tbh the only visual allegory possible is this...
November 7, 2025 at 10:51 PM
Reposted by Virginie Lucienne
You can download the models (OpenRAIL-M licence) here: huggingface.co/collections/...
Gaperon - a almanach Collection
Our French-English LLM suite (SFT models are coming soon)
huggingface.co
November 12, 2025 at 5:05 PM
Reposted by Virginie Lucienne
If you want to know more about Gaperon and the multiple experiments we carried out during the project, read Nathan's thread👇 and read our paper arxiv.org/pdf/2510.25771
Thrilled to release Gaperon, an open LLM suite for French, English and Coding 🧀

We trained 3 models - 1.5B, 8B, 24B - from scratch on 2-4T tokens of custom data

(TLDR: we cheat and get good scores)

@wissamantoun.bsky.social @rachelbawden.bsky.social @bensagot.bsky.social @zehavoc.bsky.social
November 12, 2025 at 5:05 PM
Reposted by Virginie Lucienne
First outcomes:
- Our 24B base model stands out: it outperforms open counterparts in generic generation tasks in both French and English.
- However, benchmark scores initially lagged, prompting us to investigate why some datasets seem to boost benchmarks without improving real-world generation.
November 12, 2025 at 5:05 PM
Reposted by Virginie Lucienne
We are proud to announce that we trained 1.5B, 8B, and 24B generative language models from scratch on 2 to 4 tera-tokens of carefully curated, high-quality data covering French, English and code. We release our models and code under open-source licences. Thread👇
November 12, 2025 at 5:05 PM
Reposted by Virginie Lucienne
en bref, on a entraîné une série de LLM bi-lingue fr-en, de tailles variées, entre 1.5B et 24B, quasiment du jamais vu pour une petite équipe académique et hors de très gros consortium européen. On a toute une série de résultats intéressants qui montrent que les benchmarks sont à nuancer ../..
November 8, 2025 at 9:55 AM
Reposted by Virginie Lucienne
Thrilled to release Gaperon, an open LLM suite for French, English and Coding 🧀

We trained 3 models - 1.5B, 8B, 24B - from scratch on 2-4T tokens of custom data

(TLDR: we cheat and get good scores)

@wissamantoun.bsky.social @rachelbawden.bsky.social @bensagot.bsky.social @zehavoc.bsky.social
November 7, 2025 at 9:11 PM
Reposted by Virginie Lucienne
Help team ESR, je suis à la recherche d'un.e chargée de cours pour 24h de cours bloqués sur 1 semaine en janvier: initiation à la pratique du cinéma documentaire, approche anthropologique, travail de terrain.Il s'agit d'accompagner les étudiants dans la réalisation d'un petit film. Merci pour les rt
August 27, 2025 at 6:35 AM
Reposted by Virginie Lucienne
Hi, I'm looking for 2 emergency reviews for this ARR round, both papers have only 2 reviews and neither the reviewers nor the ACs cared to acknowledge my mail insistance. Frankly, I wouldn't mind but those two papers are kind of in the verge so a third opinion is really needed. Deadline : 1-2 days
June 29, 2025 at 2:44 PM
Reposted by Virginie Lucienne
Je me permets une petite relance, toutes les pistes que j'avais cette semaine sont tombées à l'eau, j'ai l'impression que personne n'a envie de parler des règnes de Henri IV et Louis XIII 😅
Annonce un peu urgente : je cherche un.e historien.ne spécialiste du XVIIème siècle en France, si possible doctorant ou postdoc, avec de l'humour !

Si vous avez des personnes à me conseiller je suis preneuse 💜
June 20, 2025 at 10:22 AM
Reposted by Virginie Lucienne
Un violent #orage 🌩️ de #grêle s'abat #Paris. La #grêle tapisse par endroit le sol, des précipitations intenses provoquent des ruissellements urbains dans la capitale. La température a chuté de 10°C en quelques minutes. Une rafale a atteint 90 km/h au parc Montsouris (📽️Aymeric Schindler)
May 3, 2025 at 2:42 PM
Reposted by Virginie Lucienne
⛈️Paris sous un déluge de grêle pendant une trentaine de minutes avec des grêlons de 2 à 3cm.

Par ailleurs le vent a soufflé jusqu’à
99 km/h au sommet de la Tour Eiffel
90 km/h à Montsouris
66 km/h à Longchamp

📸Nadjib Louhab
📸Isabelle Batrancourt
May 3, 2025 at 2:50 PM
Reposted by Virginie Lucienne
⏰ Candidatures jusqu'au 30 avril 2025
🏆 Prix du Collège de France pour les jeunes #chercheuses et jeunes #chercheurs !
🏆 Thème 2025 : « Savoirs et #démocratie »
🏆 Dotation : 20 000 € et conférence publique au Collège de France
👉 www.college-de-france.fr/fr/actualite...
March 4, 2025 at 11:06 AM
Reposted by Virginie Lucienne
March 8, 2025 at 2:42 PM
Reposted by Virginie Lucienne
We are happy to announce our next seminar, given by Florian Cafiero @floriancafiero.bsky.social (PSL @ecoledeschartes.bsky.social) entitled "A Riddle in a Haystack: Using Large Language Models for the Detection of Rare Phenomena" on Friday 7th March at 11am CET. Details here: t.co/pPbWfkALM4!
March 5, 2025 at 12:59 PM