adding intro and futzing with some charts

app.py

@@ -172,7 +172,7 @@ def cumulative_growth_plot_analysis(df, df_compressed):
 
     # Update layout
     fig.update_layout(
-        title="Cumulative Growth of Models, Spaces, and Datasets Over Time",
+        title="Cumulative Growth of Models, Spaces, and Datasets Over Time<br><sup>Dotted lines represent growth with file-level deduplication</sup>",
         xaxis_title="Date",
         yaxis_title="Cumulative Size (PBs)",
         legend_title="Type",
@@ -242,13 +242,22 @@ def filter_by_extension_month(_df, _extension):
             fig.add_trace(
                 go.Scatter(
                     x=pivot_df.index,
-                    y=pivot_df[column] / 1e15,  # Convert to petabytes
+                    y=pivot_df[column] / 1e12,  # Convert to petabytes
                     mode="lines",
-                    name=column.capitalize(),
+                    name=column,
                     line=dict(color=px.colors.qualitative.Alphabet[i]),
                 )
             )
 
+    # Update layout
+    fig.update_layout(
+        title="Monthly Additions of LFS Files by Extension (in TBs)",
+        xaxis_title="Date",
+        yaxis_title="Size (TBs)",
+        legend_title="Type",
+        yaxis=dict(tickformat=".2f"),  # Format y-axis labels to 2 decimal places
+    )
+
     return fig
 
 
@@ -258,6 +267,13 @@ with gr.Blocks() as demo:
 
     # Add a heading
     gr.Markdown("# Git LFS Analysis Across the Hub")
+    gr.Markdown(
+        "The Hugging Face Hub has just crossed 1,000,000 models - but where is all that data stored? The short answer is Git LFS. This analysis dives into the LFS storage on the Hub, breaking down the data by repository type, file extension, and growth over time."
+    )
+
+    gr.Markdown(
+        "Now, you might ask yourself, 'Why are you doing this?' Well, the [Xet Team](https://huggingface.co/xet-team) is a [new addition to Hugging Face](https://huggingface.co/blog/xethub-joins-hf), bringing a new way to store massive datasets and models to enable ML teams to operate like software teams: Quickly and without friction. Because this story all starts with storage, that's where we've begun with our own deep dives into what the Hub holds. As part of this, we've included a look at what happens with just one simple deduplication strategy - deduplicating at the file level. Read on to see more!"
+    )
     with gr.Row():
         # scale so that
         # group the data by month and year and compute a cumulative sum of the total_size column
@@ -265,7 +281,7 @@ with gr.Blocks() as demo:
         with gr.Column(scale=1):
             gr.Markdown("# Repository Growth")
             gr.Markdown(
-                "The cumulative growth of models, spaces, and datasets over time can be seen in the adjacent chart. Beside that is a view of the total change, month to month, of LFS files stored on the hub over 2024. We're averaging nearly **2.3 PBs uploaded to LFS per month!**"
+                "The cumulative growth of models, spaces, and datasets over time can be seen in the adjacent chart. Beside that is a view of the total change, from the previous month to the current one, of LFS files stored on the hub over 2024. We're averaging nearly **2.3 PBs uploaded to LFS per month!**"
             )
             gr.Dataframe(last_10_months, height=250)
         with gr.Column(scale=3):
@@ -328,4 +344,6 @@ with gr.Blocks() as demo:
     )
     _by_extension_month = gr.State(by_extension_month)
     gr.Plot(filter_by_extension_month, inputs=[_by_extension_month, extension])
+
+# launch the dang thing
 demo.launch()