14 1 49

Alexander Visheratin

visheratin

AI & ML interests

None yet

Recent Activity

updated a model 22 days ago

visheratin/mexma-siglip

updated a model 22 days ago

visheratin/nllb-clip-large-siglip

View all activity

Articles

Data exploration and filtering with Nomic Atlas

Mar 22

• 4

Breaking resolution curse of vision-language models

Feb 24

• 11

Organizations

visheratin's activity

updated 2 models 22 days ago

visheratin/mexma-siglip

Zero-Shot Image Classification • Updated 22 days ago • 293 • 3

visheratin/nllb-clip-large-siglip

Zero-Shot Image Classification • Updated 22 days ago • 616 • 4

updated a model 7 months ago

visheratin/nllb-siglip-i18n

Zero-Shot Image Classification • Updated Jun 3 • 2 • 1

updated a model 8 months ago

visheratin/nllb-clip-base-siglip

Zero-Shot Image Classification • Updated May 3 • 566 • 1

liked a dataset 8 months ago

google/docci

Updated Jul 24 • 393 • 63

liked a model 8 months ago

qnguyen3/nanoLLaVA

Text Generation • Updated Oct 27 • 22.7k • 150

updated a dataset 8 months ago

visheratin/documentation-images

Viewer • Updated Apr 16 • 1 • 4.19k

liked a dataset 8 months ago

HuggingFaceM4/the_cauldron

Viewer • Updated May 6 • 1.88M • 89.1k • 350

liked a dataset 9 months ago

visheratin/realworldqa

Viewer • Updated Apr 13 • 765 • 97 • 33

posted an update 9 months ago

Post

3241

Yesterday, xAI announced Grok-1.5 Vision - https://x.ai/blog/grok-1.5v. But more importantly, they also released a new VLM benchmark dataset - RealWorldQA. The only problem was that they released it as a ZIP archive. I fixed that! Now you can use it in your evaluations as a regular HF dataset: visheratin/realworldqa