Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for review of SAM3 access application
#364
by aadit92 - opened
Huggingface username: aadit92
Dear Team,
I am a volunteer at Ocean Park in Hong Kong and a recent graduate from the Hong Kong University of Science and Technology. I am working on a project involving the analysis of dolphin vocalisations—I requested access to SAM 3 as I believe it would be the perfect tool for text-prompted acoustic spectrogram analysis. I will comply with the SAM license and model terms and only use the model for non-commercial purposes.
I would greatly appreciate it if you could manually review my rejected request.
Many thanks.