Instructions to use CollectionStudio/sam2-hiera-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CollectionStudio/sam2-hiera-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="CollectionStudio/sam2-hiera-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("CollectionStudio/sam2-hiera-large") model = AutoModel.from_pretrained("CollectionStudio/sam2-hiera-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from CollectionStudio/sam2-hiera-large: direct link, hf CLI and curl.
- Browser
- Download file 95 Bytes
-
https://huggingface.co/CollectionStudio/sam2-hiera-large/resolve/main/processor_config.json
- Command line
-
hf download hf://CollectionStudio/sam2-hiera-large/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/CollectionStudio/sam2-hiera-large/resolve/main/processor_config.json
95 Bytes
| { | |
| "point_pad_value": -10, | |
| "processor_class": "Sam2VideoProcessor", | |
| "target_size": 1024 | |
| } | |