Hugging Face's logo

nkkbr
/
ViCA-ARKitScenes

Video-Text-to-Text
Transformers
Safetensors
English
llava
text-generation
multimodal
vision-language
video understanding
spatial reasoning
visuospatial cognition
qwen
llava-video
Model card Files
xet
 Community
How to use from the
Use from the
Transformers library
# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("nkkbr/ViCA-ARKitScenes")
model = AutoModelForCausalLM.from_pretrained("nkkbr/ViCA-ARKitScenes", device_map="auto")
Quick Links

Usage and Full Documentation

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

nkkbr/ViCA

Downloads last month
16
Safetensors
Model size
8B 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-ARKitScenes

Base model

lmms-lab/llava-onevision-qwen2-7b-si
Finetuned
lmms-lab/LLaVA-Video-7B-Qwen2
Finetuned
(15)
this model

Datasets used to train nkkbr/ViCA-ARKitScenes

Collection including nkkbr/ViCA-ARKitScenes