Upload README.md with huggingface_hub

README.md

@@ -48,7 +48,8 @@ Five ground-roll intensity levels produce paired noisy / noise-label records:
 
 ## Model Architectures
 
-- **Enhanced Atten-UNet** (`enhanced_atten_unet`) — U-Net with residual blocks + attention-gated skip connections, trained with hybrid MSE + AFM (adaptive frequency modulation) loss. Base channels: 32, depth: 4.
+- **DDPM cDDPM** (`ddpm`) — Conditional DDPM (DDPM-2c) jointly modeling signal and ground-roll distributions. Modified U-Net with time embedding, self-attention bottleneck, 5 ResNet levels.
+- **physics** (`physics`) — 
 
 ### Preprocessing