Use Blocks instead of Interface

To add a collapseable markdown note, build our own interface with
Blocks, so we can add an Accordion element with the markdown in it.

app.py

@@ -67,13 +67,22 @@ tokenizer = GPT2TokenizerFast.from_pretrained(model_id)
 dataset = CrowSPairsDataset()
 
 bias_type_sel = gradio.Dropdown(label="Bias Type", choices=dataset.bias_types())
-
-iface = gradio.Interface(
-    fn=run,
-    inputs=bias_type_sel,
-    outputs="html",
-    title="Detecting stereotypes in the GPT-2 language model using CrowS-Pairs",
-    description="GPT-2 is a language model which can score how likely it is that some text is a valid English sentence: not only grammaticality, but also the 'meaning' of the sentence is part of this score. CrowS-Pairs is a dataset with pairs of more and less stereotypical examples for different social groups (e.g., gender and nationality stereotypes). We sample 10 random pairs from CrowS-Pairs and show whether the stereotypical example gets a higher score ('is more likely'). If GPT-2 systematically prefers the stereotypical examples, it has probably learnt these stereotypes from the training data.",
-)
+with open("description.md") as fh:
+    desc = fh.read()
+
+with open("notice.md") as fh:
+    notice = fh.read()
+
+with gradio.Blocks() as iface:
+    gradio.Markdown(desc)
+    with gradio.Row(equal_height=True):
+        with gradio.Column(scale=4):
+            inp = gradio.Dropdown(label="Bias Type", choices=dataset.bias_types())
+        with gradio.Column(scale=1):
+            but = gradio.Button("Sample")
+    out = gradio.HTML()
+    but.click(run, inp, out)
+    with gradio.Accordion("A note about explainability models"):
+        gradio.Markdown(notice)
 
 iface.launch()

description.md

@@ -0,0 +1,3 @@
+# Detecting stereotypes in the GPT-2 language model using CrowS-Pairs
+
+GPT-2 is a language model which can score how likely it is that some text is a valid English sentence: not only grammaticality, but also the 'meaning' of the sentence is part of this score. CrowS-Pairs is a dataset with pairs of more and less stereotypical examples for different social groups (e.g., gender and nationality stereotypes). We sample 10 random pairs from CrowS-Pairs and show whether the stereotypical example gets a higher score ('is more likely'). If GPT-2 systematically prefers the stereotypical examples, it has probably learnt these stereotypes from the training data.

notice.md

@@ -0,0 +1,3 @@
+# AI still stupid
+
+don't get fooled; it's all just numbers