Vision-Language Modeling - a deepvk Collection

deepvk 's Collections

Vision-Language Modeling

Sentence Encoders

Vision-Language Modeling

updated 21 days ago

Our datasets and models for Visual-Language Modeling

deepvk/LLaVA-Instruct-ru

Viewer • Updated May 22 • 144k • 5 • 5

Note GPT-based instruction dataset for LLaVA-style training
deepvk/GQA-ru

Viewer • Updated 25 days ago • 80.1k • 69 • 3

Note Translated version of GQA benchmark
deepvk/MMBench-ru

Viewer • Updated 27 days ago • 3.91k • 70 • 2

Note Translated version of MMBench benchmark