Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -72,6 +72,14 @@ with gr.Blocks(theme='snehilsanyal/scikit-learn') as app:
|
|
72 |
[chatbot,text_box,image_box],
|
73 |
chatbot
|
74 |
)
|
75 |
-
gr.Markdown("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
app.queue()
|
77 |
app.launch()
|
|
|
72 |
[chatbot,text_box,image_box],
|
73 |
chatbot
|
74 |
)
|
75 |
+
gr.Markdown("""
|
76 |
+
# Multimodal Chain-of-Thought Reasoning in Language Models
|
77 |
+
|
78 |
+
<h5 align="center"><i>"Imagine learning a textbook without figures or tables."</i></h5>
|
79 |
+
|
80 |
+
Multimodal-CoT incorporates vision features in a decoupled training framework. The framework consists of two training stages: (i) rationale generation and (ii) answer inference. Both stages share the same model architecture but differ in the input and output.
|
81 |
+
""")
|
82 |
+
|
83 |
+
|
84 |
app.queue()
|
85 |
app.launch()
|