Image Feature Extraction
Transformers
SMARTIES-v1-ViT-B
earth-observation
remote-sensing
foundation-model
multi-sensor
custom_code
Instructions to use gsumbul/SMARTIES-v1-ViT-L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gsumbul/SMARTIES-v1-ViT-L with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="gsumbul/SMARTIES-v1-ViT-L", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("gsumbul/SMARTIES-v1-ViT-L", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from gsumbul/SMARTIES-v1-ViT-L: direct link, hf CLI and curl.
- Browser
- Download file 621 Bytes
-
https://huggingface.co/gsumbul/SMARTIES-v1-ViT-L/resolve/main/config.json
- Command line
-
hf download hf://gsumbul/SMARTIES-v1-ViT-L/config.json
-
curl -L -o config.json https://huggingface.co/gsumbul/SMARTIES-v1-ViT-L/resolve/main/config.json
621 Bytes
| { | |
| "model_type": "SMARTIES-v1-ViT-B", | |
| "auto_map": { | |
| "AutoModel": "smarties_model.SMARTIESHF", | |
| "AutoConfig": "smarties_config.SMARTIESConfig" | |
| }, | |
| "transformers_weights": "smarties-v1-vitl.safetensors", | |
| "spectrum_specs": null, | |
| "img_size": 224, | |
| "patch_size": 16, | |
| "embed_dim": 1024, | |
| "depth": 24, | |
| "num_heads": 16, | |
| "mlp_ratio": 4.0, | |
| "qkv_bias": true, | |
| "norm_eps": 1e-6, | |
| "global_pool": false, | |
| "norm_layer_eps": 1e-6, | |
| "pos_drop_rate": 0.0, | |
| "mixed_precision": "no", | |
| "decoder_embed_dim": 512, | |
| "decoder_depth": 8, | |
| "decoder_num_heads": 16 | |
| } |