Update README.md

README.md

@@ -293,6 +293,25 @@ ViCA-7B supports a broad range of spatially grounded multimodal applications:
 - No depth/point cloud: Only RGB video input supported  
 - Zero-shot generalization is good, but not task-agnostic
 
+##  Download
+
+You can download the model weights to your local environment (optional).
+
+```python
+from huggingface_hub import snapshot_download
+
+save_dir = "./ViCA"
+repo_id = "nkkbr/ViCA"
+cache_dir = save_dir + "/cache"
+
+snapshot_download(cache_dir=cache_dir,
+  local_dir=save_dir,
+  repo_id=repo_id,
+  local_dir_use_symlinks=False,
+  resume_download=True,
+)
+```
+
 ## Inference
 
 *Here is a runnable example using ViCA-7B on a VSI-Bench question.*