README.md

# My CLIP Video-Text Model

This model was trained on the MSR-VTT dataset using a custom CLIP-based architecture.

self.video_proj = nn.Sequential(
            nn.Linear(512, 2048),
            nn.ReLU(),
            nn.Linear(2048, 2048),
            nn.ReLU(),
            nn.Linear(2048, 512)
        )