Update app.py
Browse files
app.py
CHANGED
|
@@ -129,7 +129,13 @@ def create_leaderboard():
|
|
| 129 |
|
| 130 |
# Create Gradio interface with a nice theme
|
| 131 |
with gr.Blocks(theme=gr.themes.Soft(), title="Financial Model Performance Leaderboard") as demo:
|
| 132 |
-
gr.Markdown(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
gr.HTML("""
|
| 134 |
<div style="padding: 20px;">
|
| 135 |
<h2>About This Leaderboard</h2>
|
|
|
|
| 129 |
|
| 130 |
# Create Gradio interface with a nice theme
|
| 131 |
with gr.Blocks(theme=gr.themes.Soft(), title="Financial Model Performance Leaderboard") as demo:
|
| 132 |
+
gr.Markdown(
|
| 133 |
+
"""<div style="text-align: center;"><h1>Financial <span style='color: #e6b800;'>Code</span> Models <span style='color: #e6b800;'> Performance Leaderboard</span></h1></div>\
|
| 134 |
+
<br>\
|
| 135 |
+
<p>Inspired by the <a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">🤗 Open LLM Leaderboard</a> and <a href="https://huggingface.co/spaces/optimum/llm-perf-leaderboard">🤗 Open LLM-Perf Leaderboard 🏋️</a>, we evaluate model performance using <a href="https://huggingface.co/papers/2502.06329">FailSafe Long Context QA</a>. This evaluation leverages the <a href="https://huggingface.co/datasets/Writer/FailSafeQA">FailSafeQA dataset</a> to assess how well models handle long-context question answering, ensuring robust and reliable performance in extended-context scenarios.</p>
|
| 136 |
+
""",
|
| 137 |
+
elem_classes="markdown-text",
|
| 138 |
+
)
|
| 139 |
gr.HTML("""
|
| 140 |
<div style="padding: 20px;">
|
| 141 |
<h2>About This Leaderboard</h2>
|