Dataset stats: \
lat_mean = 39.951564548022596 \
lat_std = 0.0006361722351128644 \
lon_mean = -75.19150880602636 \
lon_std = 0.000611411894337979 

The model can be loaded using:
```
from huggingface_hub import hf_hub_download
import torch

# Specify the repository and the filename of the model you want to load
repo_id = "FinalProj5190/vit_base_72"  # Replace with your repo name
filename = "resnet_gps_regressor_complete.pth"

model_path = hf_hub_download(repo_id=repo_id, filename=filename)

model_test = MultiModalModel()
model_test.load_state_dict(torch.load(model_path))
model_test.eval()
```

The model implementation is here:
```
from transformers import AutoModel

class MultiModalModel(nn.Module):
    def __init__(self, image_model_name='google/vit-base-patch16-224-in21k', output_dim=2):
        super(MultiModalModel, self).__init__()

        # Load Vision Transformer for feature extraction
        self.image_model = AutoModel.from_pretrained(image_model_name, output_hidden_states=True)

        # Combine image and GPS features for regression
        self.regressor = nn.Sequential(
            nn.Linear(self.image_model.config.hidden_size, 128),
            nn.ReLU(),
            nn.Dropout(0.3),
            nn.Linear(128, output_dim),
        )

    def forward(self, image):
        # Extract image features from the last hidden state
        image_outputs = self.image_model(image)
        image_features = image_outputs.last_hidden_state[:, 0, :]  # CLS token features

        # Final regression
        return self.regressor(image_features)
```