Alexander Visheratin's picture

Alexander Visheratin

visheratin

·

AI & ML interests

None yet

Articles

Data exploration and filtering with Nomic Atlas

Breaking resolution curse of vision-language models

Organizations

Posts 5

Post

3189

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

Post

1937

Look at the beauty in the video — four different embeddings on the same map! In another community blog post, I explore how you can use Nomic Atlas to view and clean your dataset. You can check it out here - https://huggingface.co/blog/visheratin/nomic-data-cleaning

Papers 1

arxiv:2309.01859

spaces 2

Mc Llava 3b

Laion Nllb

models 18

visheratin/nllb-siglip-i18n

Zero-Shot Image Classification • Updated Jun 3 • 6

visheratin/nllb-clip-large-siglip

Zero-Shot Image Classification • Updated May 3 • 1.69k • 2

visheratin/nllb-clip-base-siglip

Zero-Shot Image Classification • Updated May 3 • 943 • 1

visheratin/mc-llava-3b-ft

Feature Extraction • Updated Mar 24 • 2

visheratin/nllb-siglip-mrl-large

Zero-Shot Image Classification • Updated Mar 10 • 1.34k • 12

visheratin/nllb-siglip-mrl-base

Zero-Shot Image Classification • Updated Mar 10 • 977 • 8

visheratin/MC-LLaVA-3b

Updated Feb 28 • 342 • 83

visheratin/nllb-clip-large-oc

Zero-Shot Image Classification • Updated Oct 24, 2023 • 32 • 2

visheratin/nllb-clip-base-oc

Zero-Shot Image Classification • Updated Oct 24, 2023 • 37 • 1

visheratin/nllb-clip-base

Updated Oct 11, 2023 • 313 • 4

datasets 11

visheratin/documentation-images

Viewer • Updated Apr 16 • 1 • 4.95k

visheratin/realworldqa

Viewer • Updated Apr 13 • 765 • 88 • 31

visheratin/laion-coco-nllb

Viewer • Updated Apr 11 • 894k • 1.18k • 39

visheratin/nllb-coco-long

Viewer • Updated Apr 9 • 45.7k • 60

visheratin/SVIT

Viewer • Updated Mar 31 • 108k • 44

visheratin/google_landmarks_photos

Viewer • Updated Mar 19 • 1.27M • 55 • 2

visheratin/object_questions

Viewer • Updated Mar 17 • 132k • 48

visheratin/uber_text_qa

Viewer • Updated Mar 16 • 9.98k • 58 • 1

visheratin/google_landmarks_places

Viewer • Updated Mar 16 • 35.1k • 63 • 2

visheratin/unsplash-caption-questions-init

Viewer • Updated Feb 28 • 24.9k • 46