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
- Xet hash:
- 766d35eb308320a6cf792577bcd0a5846178b8ed8691116efb85a6bbf73928b2
- Size of remote file:
- 4.97 GB
- SHA256:
- 6a9eb4ae0e47d9ddaf43a04e2b5771d789f0d19d75ea1d1ead30a7c343fc440b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.