nkkbr
/

ViCA-ScanNet

Video-Text-to-Text

text-generation

vision-language

video understanding

spatial reasoning

visuospatial cognition

Model card Files Files and versions

Usage and Full Documentation

For detailed model description, training setup, datasets, evaluation results, and inference code, please refer to the main ViCA-7B README:

Downloads last month: 6

Safetensors

Model size

8.03B params

Tensor type

BF16

·

Inference Providers NEW

Video-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nkkbr/ViCA-ScanNet

Base model

lmms-lab/llava-onevision-qwen2-7b-si

Finetuned

lmms-lab/LLaVA-Video-7B-Qwen2

Finetuned

(12)

this model

Datasets used to train nkkbr/ViCA-ScanNet

Collection including nkkbr/ViCA-ScanNet

ViCA

A 7B vision-language model with strong visuospatial reasoning capabilities. • 6 items • Updated May 6