Video-Text-to-Text
Transformers
Safetensors
English
llava
text-generation
multimodal
vision-language
video understanding
spatial reasoning
visuospatial cognition
qwen
llava-video
Instructions to use nkkbr/ViCA-ScanNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nkkbr/ViCA-ScanNet with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("nkkbr/ViCA-ScanNet") model = AutoModelForCausalLM.from_pretrained("nkkbr/ViCA-ScanNet", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download merges.txt from nkkbr/ViCA-ScanNet: direct link, hf CLI and curl.
- Browser
- Download file 1.67 MB
-
https://huggingface.co/nkkbr/ViCA-ScanNet/resolve/main/merges.txt
- Command line
-
hf download hf://nkkbr/ViCA-ScanNet/merges.txt
-
curl -L -o merges.txt https://huggingface.co/nkkbr/ViCA-ScanNet/resolve/main/merges.txt
1.67 MB
File too large to display, you can check the raw version instead.