Raphael Sourty's picture

Raphael Sourty

raphaelsty

·

https://github.com/raphaelsty

AI & ML interests

NLP, KG, Online Machine Learning

Recent Activity

liked a model about 1 hour ago

Qwen/Qwen3-0.6B

liked a dataset about 6 hours ago

lightonai/embeddings-fine-tuning

upvoted a collection about 7 hours ago

DenseOn & LateOn

View all activity

Organizations

upvoted a collection about 7 hours ago

DenseOn & LateOn

A collection of open state-of-the-art single and multi-vector models • 7 items • Updated 2 days ago • 8

upvoted an article 2 days ago

Article

DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models

2 days ago

•

30

upvoted an article 7 days ago

Article

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

8 days ago

•

63

upvoted a collection 21 days ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 1 day ago • 155

upvoted a paper 29 days ago

ByT5: Towards a token-free future with pre-trained byte-to-byte models

Paper • 2105.13626 • Published May 28, 2021 • 5

upvoted a collection about 2 months ago

pplx-embed

Diffusion-Pretrained Dense and Contextual Embeddings • 7 items • Updated Feb 26 • 96

upvoted a collection 2 months ago

LateOn-Code 💻

State-of-the-art late interaction code retrieval models • 6 items • Updated 16 days ago • 18

upvoted an article 2 months ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

Feb 12

•

54

upvoted 2 articles 3 months ago

Article

🥃 Distilling Tiny Embeddings

Jan 10

•

22

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

Jan 19

•

92

upvoted an article 6 months ago

Article

Sentence Transformers is joining Hugging Face!

Oct 22, 2025

•

88

upvoted a collection 10 months ago

PyLate 🐕

State-of-the-art late interaction models trained using PyLate • 5 items • Updated 16 days ago • 4