Spaces:
Sleeping
Sleeping
sunmarinup commited on
Commit ·
7187401
1
Parent(s): 9e60ee8
Change layout
Browse files- app.py +1 -2
- src/about.py +1 -8
app.py
CHANGED
|
@@ -77,13 +77,12 @@ def create_app():
|
|
| 77 |
datatype="markdown",
|
| 78 |
label="Leaderboard",
|
| 79 |
elem_id="leaderboard-table",
|
|
|
|
| 80 |
)
|
| 81 |
|
| 82 |
status_text = gr.Markdown()
|
| 83 |
-
refresh_button = gr.Button("Refresh leaderboard", variant="primary")
|
| 84 |
|
| 85 |
demo.load(refresh_leaderboard, outputs=[leaderboard_table, status_text])
|
| 86 |
-
refresh_button.click(refresh_leaderboard, outputs=[leaderboard_table, status_text])
|
| 87 |
|
| 88 |
return demo
|
| 89 |
|
|
|
|
| 77 |
datatype="markdown",
|
| 78 |
label="Leaderboard",
|
| 79 |
elem_id="leaderboard-table",
|
| 80 |
+
show_search="search",
|
| 81 |
)
|
| 82 |
|
| 83 |
status_text = gr.Markdown()
|
|
|
|
| 84 |
|
| 85 |
demo.load(refresh_leaderboard, outputs=[leaderboard_table, status_text])
|
|
|
|
| 86 |
|
| 87 |
return demo
|
| 88 |
|
src/about.py
CHANGED
|
@@ -1,12 +1,5 @@
|
|
| 1 |
-
# Your leaderboard name
|
| 2 |
TITLE = """<h1 align="center" id="space-title">Upgini MLE-Bench Tabular Leaderboard</h1>"""
|
| 3 |
|
| 4 |
-
# What does your leaderboard evaluate?
|
| 5 |
INTRODUCTION_TEXT = """
|
| 6 |
-
This
|
| 7 |
-
Click **Refresh leaderboard** any time to re-download the CSV from GitHub.
|
| 8 |
-
"""
|
| 9 |
-
|
| 10 |
-
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
|
| 11 |
-
CITATION_BUTTON_TEXT = r"""
|
| 12 |
"""
|
|
|
|
|
|
|
| 1 |
TITLE = """<h1 align="center" id="space-title">Upgini MLE-Bench Tabular Leaderboard</h1>"""
|
| 2 |
|
|
|
|
| 3 |
INTRODUCTION_TEXT = """
|
| 4 |
+
This leaderboard mirrors the latest changes to [Upgini's MLE-Bench](https://github.com/upgini/mle-bench) leaderboard. It is a version of [MLE-bench](https://github.com/openai/mle-bench) that compares agent performance on tabular data. It uses exactly the same setup and differs just in the leaderboard view. We focus on tabular tasks and use [normalized score](https://github.com/upgini/mle-bench/?tab=readme-ov-file#mean-normalized-score) instead of medal percentage to compare differently scaled scores. The leaderboard is recomputed upon updating submitted runs from OpenAI repo.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"""
|