Video-Text-to-Text
Transformers
Safetensors
English
llava
text-generation
multimodal
vision-language
video understanding
spatial reasoning
visuospatial cognition
qwen
llava-video
Eval Results (legacy)
Instructions to use nkkbr/ViCA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nkkbr/ViCA with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("nkkbr/ViCA") model = AutoModelForCausalLM.from_pretrained("nkkbr/ViCA") - Notebooks
- Google Colab
- Kaggle

- Xet hash:
- a72b523d22fc272584bff1c56d03180dc3be12768d1d54e69e868425ef5d2007
- Size of remote file:
- 587 kB
- SHA256:
- 2e8c4c5e9ef49ddf256ad5006536800feed6b3153af9c9b78395e66bf106f637
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.