Instructions to use moonshotai/MoonViT-SO-400M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moonshotai/MoonViT-SO-400M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="moonshotai/MoonViT-SO-400M", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("moonshotai/MoonViT-SO-400M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoImageProcessor": "image_processing_moonvit.MoonViTImageProcessor" | |
| }, | |
| "in_token_limit": 4096, | |
| "patch_size": 14, | |
| "num_pooled_tokens": 1024, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "pad_input": true | |
| } |