Update app.py

app.py

@@ -2,6 +2,12 @@ import gradio as gr
 import matplotlib.pyplot as plt
 import numpy as np
 
+INTRO = """# Harm's law 
+
+The Chinchilla scaling laws focus on optimally scaling training compute but often we also care about inference cost. 
+This tool follows [Harm de Vries' blog post](https://www.harmdevries.com/post/model-size-vs-compute-overhead/) and visualizes the tradeoff between training comput and inference cost (i.e. model size). 
+"""
+
 ### CHINCHILLA PARAMS:
 E = 1.62
 A = 406.4
@@ -80,10 +86,7 @@ Inference cost fraction:\t {kn*100:.2f}%"""
     return text, fig
 
 with gr.Blocks() as demo:
-    gr.Markdown("# Harm's law\
-The Chinchilla scaling laws focus on optimally scaling training compute but often we also care about inference cost. 
-This tool follows [Harm de Vries' blog post](https://www.harmdevries.com/post/model-size-vs-compute-overhead/) and visualizes the tradeoff between training comput and inference cost (i.e. model size). 
-")
+    gr.Markdown(INTRO)
     N = gr.Number(value=1, label="Model size (in B parameters):")
     D = gr.Number(value=100, label="Dataset size (in B tokens):")
     button = gr.Button("Compute!")