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 Reconsideration of Gated Model Access β @junkrat77
Hello SAM 3 team,
My request to access facebook/sam3 was recently rejected. I would be grateful if you could reconsider the decision, or reset my access request so that I can submit any missing or corrected information.
Intended use:
I am reproducing the ASPIRE LIBERO-Pro Goal-Swap Quick Start benchmark across all ten tasks. SAM 3 is a required dependency for visual perception and segmentation in this robotics simulation experiment. The model will be used solely for NON-COMMERCIAL ACADEMIC RESEARCH.
I will comply with the applicable license, acceptable-use policy, and access conditions. I will store the checkpoint securely and will not redistribute, publish, or provide unauthorized access to the model weights.
If my original request was rejected because any profile or application information was incomplete or unclear, please let me know what needs to be updated. I would sincerely appreciate reconsideration or an opportunity to resubmit the request.
Hugging Face username: junkrat77
Thank you for your time.