Merve Noyan

mervenoyan

AI & ML interests

My actual account is hf.co/merve this account is opened before I started working at HF, sometimes I accidentally open PRs here lol

Recent Activity

liked a model 8 days ago

nanonets/Nanonets-OCR-s

liked a model 8 days ago

prithivMLmods/Qwen2-VL-OCR-2B-Instruct

liked a model 9 days ago

DatologyAI/retr-opt-vit-b-32

View all activity

Organizations

liked 2 models 8 days ago

nanonets/Nanonets-OCR-s

Image-Text-to-Text • Updated 5 days ago • 177k • 1.18k

prithivMLmods/Qwen2-VL-OCR-2B-Instruct

Image-Text-to-Text • Updated May 2 • 79.9k • 90

liked 2 models 9 days ago

DatologyAI/retr-opt-vit-b-32

Zero-Shot Image Classification • Updated 16 days ago • 127 • 7

DatologyAI/cls-opt-vit-b-32

Zero-Shot Image Classification • Updated 16 days ago • 112 • 6

New activity in yigitbekir/Bert2D-cased-Turkish-128K-WWM-NSW2 9 days ago

Update tokenizer_config.json

#2 opened 9 days ago by

mervenoyan

New activity in kernels-community/README 10 days ago

Update README.md

#2 opened 10 days ago by

mervenoyan

upvoted a paper 22 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 24 days ago • 100

upvoted an article 24 days ago

Article

AI Policy @🤗: Response to the 2025 National AI R&D Strategic Plan

and 2 others •

24 days ago

• 13

New activity in transformers-community/support about 1 month ago

Latest vision & multimodal releases in transformers

🔥 2

#8 opened about 1 month ago by

mervenoyan

upvoted an article about 1 month ago

Article

How to generate text: using different decoding methods for language generation with Transformers

•

Mar 1, 2020

• 218

New activity in nvidia/DAM-3B-Video 2 months ago

Add license

#1 opened 2 months ago by

mervenoyan

New activity in nvidia/DAM-3B 2 months ago

Add license

#2 opened 2 months ago by

mervenoyan

Code snippet to use the model

❤️ 8

#1 opened 2 months ago by

mervenoyan

New activity in nvidia/DAM-3B-Self-Contained 2 months ago

License

❤️ 1

#1 opened 2 months ago by

merve

posted an update 2 months ago

Post

585

Why do people sleep on DSE multimodal retrieval models? 👀

They're just like ColPali, but highly scalable, fast and you can even make them more efficient with binarization or matryoshka with little degradation 🪆

I made a small collection of them so you can get started merve/multimodal-dse-retrievers-67fe71a9c8f1ad26a48859c3

Image taken from MCDSE blog https://huggingface.co/blog/marco/announcing-mcdse-2b-v1