Image Segmentation
Transformers
Safetensors
multilingual
sa2va_chat
feature-extraction
Sa2VA
custom_code
dense-grounding
referring-expression-segmentation
Instructions to use kumuji/Sa2VA-i-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kumuji/Sa2VA-i-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="kumuji/Sa2VA-i-4B", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("kumuji/Sa2VA-i-4B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K