Feature Extraction
Transformers
Safetensors
English
closp
remote-sensing
text-to-image-retrieval
multimodal
geospatial
SAR
multispectral
crisis-management
earth-observation
contrastive-learning
custom_code
Instructions to use DarthReca/GeoCLOSP-RN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DarthReca/GeoCLOSP-RN with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DarthReca/GeoCLOSP-RN", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DarthReca/GeoCLOSP-RN", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "closp/geoclosp-rn", | |
| "architectures": [ | |
| "CLOSPModel" | |
| ], | |
| "location_embedding_dim": 256, | |
| "logit_scale_init_value": 1.0, | |
| "model_type": "closp", | |
| "projection_dim": 384, | |
| "s1_embedding_dim": 1000, | |
| "s1_head_dim": 1000, | |
| "s2_embedding_dim": 1000, | |
| "s2_head_dim": 1000, | |
| "text_model_name_or_path": "sentence-transformers/all-MiniLM-L6-v2", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.1", | |
| "use_location_encoder": true, | |
| "vision_model_key": "resnet50", | |
| "auto_map": { | |
| "AutoModel": "modeling_closp.CLOSPModel", | |
| "AutoConfig": "modeling_closp.CLOSPConfig" | |
| } | |
| } | |