Updating description

app.py

@@ -242,10 +242,7 @@ def create_visualization(blt_ps, d_model_slider, local_n_layers_slider):
 with gr.Blocks(title="BLT vs BPE FLOPs Comparison") as demo:
     gr.Markdown("""
     # BLT vs BPE FLOPs Comparison
-
-    This interactive visualization compares the computational efficiency (FLOPs per byte) and total model parameters between:
-    - **BPE (Byte Pair Encoding)**: Traditional transformer architecture
-    - **BLT (Byte Latent Transformer)**: Novel architecture with Global and Local components with a dynamic patch size to segment bytes.
+    Companion blog post [can be found here](https://lucalp.dev/bitter-lesson-tokenization-and-blt).
 
     For inspiration, have a look at the paper's [BLT architecture configurations](https://arxiv.org/html/2412.09871v1#:~:text=%5Cbeginappendix-,11,Table%C2%A010%20shows%20different%20hyper%20parameter%20settings%20for%20BLT%20models.,-Encoder) for some inspiration.
 
@@ -253,6 +250,7 @@ with gr.Blocks(title="BLT vs BPE FLOPs Comparison") as demo:
     1. Patch size reduces global model FLOPs but not local model
     2. Increasing patch size and global model dimension doesn't change total FLOPs
     3. In smaller BLTs, local models constitute a larger portion of the total FLOPs
+
     Parameter counts are displayed below each bar.
     """)