Stéphan Tulkens

stephantulkens

·

https://stephantul.github.io

stephantul

AI & ML interests

Sentence embeddings Efficiency Static word embeddings

Recent Activity

liked a model about 3 hours ago

arcee-ai/Trinity-Mini

liked a dataset 2 days ago

TeraflopAI/web-page-quality-labels

liked a model 5 days ago

fastino/gliner2.5-multi-v1

View all activity

Organizations

upvoted a collection about 1 month ago

POTION onnx

onnx versions of our potion models, for use in Fastembed or other packages • 4 items • Updated 22 days ago • 2

upvoted an article about 1 month ago

Article

mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench

hotchpotch

•

Aug 13

• 10

upvoted an article about 2 months ago

Article

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

erikkaum

•

Aug 7

• 19

upvoted a collection 11 months ago

NIFE models

Nearly Inference Free Embedding (NIFE) models trained using pyNIFE: github.com/stephantul/pynife • 2 items • Updated Nov 4, 2025 • 2

upvoted an article 11 months ago

Article

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

isaacchung

•

Oct 20, 2025

• 38

upvoted a paper 12 months ago

HUME: Measuring the Human-Model Performance Gap in Text Embedding Task

Paper • 2510.10062 • Published Oct 11, 2025 • 10

upvoted a collection 12 months ago

Mxbai-large-v1 EmbedPress

Large datasets of mxbai-large-v1 embeddings with their truncated texts. Useful for distillation • 13 items • Updated Oct 24, 2025 • 2

upvoted an article 12 months ago

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

+4

fzliu, KennethEnevoldsen, Samoed, isaacchung, tomaarsen, fzoll

•

Oct 1, 2025

• 149

upvoted a collection over 1 year ago

The Ultimate Collection of Code Classifiers

🔥 15 classifiers, 124M parameters, one per programming language— for assessing the educational value of GitHub code • 15 items • Updated May 5, 2025 • 16

upvoted 3 articles over 1 year ago

Article

Introducing EuroBERT: A High-Performance Multilingual Encoder Model

EuroBERT

•

Mar 10, 2025

• 150

Article

1 Billion Classifications

derek-thomas

•

Feb 13, 2025

• 46

Article

Agentic RAG Stack (1/5) - Index and retrieve documents for vector search using Sentence Transformers and DuckDB

davidberenstein1957

•

Jan 27, 2025

• 22

upvoted 3 collections almost 2 years ago

Models for dataset curation

9 items • Updated Dec 5, 2024 • 17

POTION

These are the flagship POTION models. Load them and use them with model2vec (https://github.com/MinishLab/model2vec) or sentence-transformers • 9 items • Updated 13 days ago • 16

NanoBEIR 🍺

A collection of smaller versions of BEIR datasets with 50 queries and up to 10K documents each. • 13 items • Updated Sep 11, 2024 • 27

upvoted an article almost 2 years ago

Article

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

Pringled

•

Oct 14, 2024

• 105

upvoted a collection almost 2 years ago

Model2Vec base models

These are the Minishlab Model2Vec base models. Load them and use them with model2vec (https://github.com/MinishLab/model2vec) or sentence-transformers • 11 items • Updated 22 days ago • 9