| # CLIP-RS Model Metadata | |
| name: CLIP-RS | |
| version: 1.0.0 | |
| description: Vision-Language Pre-training with Data Purification for Remote Sensing | |
| model_type: clip | |
| base_model: openai/clip-vit-large-patch14-336 | |
| training_dataset: CLIP-RS-10M | |
| developer: WHU-RS institute for AI and Machine Vision |