Update blog

Author: cmdr2

content/blog/2025-11-07-1762514507.md

@@ -15,6 +15,23 @@ Wrote a simple script to convert ONNX to GGML. It auto-generates C++ code that c
 
 The generated file can work on multiple backends: CPU, CUDA, ROCm, Vulkan, Metal etc, by providing the correct compiler flags during `cmake -B`, e.g. `-D GGML_CUDA=1` for CUDA.
 
+The original PyTorch model was:
+
+```py
+class TinyCNN(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.conv = nn.Conv2d(3, 8, 3, stride=1, padding=1)
+        self.relu = nn.ReLU()
+        self.pool = nn.AdaptiveAvgPool2d((1, 1))
+        self.fc = nn.Linear(8, 4)  # 4-class toy output
+
+    def forward(self, x):
+        x = self.relu(self.conv(x))
+        x = self.pool(x).flatten(1)
+        return self.fc(x)
+```
+
 Repo: [https://github.com/cmdr2/graph-compiler](https://github.com/cmdr2/graph-compiler)
 
 I've currently got it to work for a TinyCNN model, and will add more operators as I make it convert larger models.