Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
pminervini
commited on
Commit
β’
9af5ebf
1
Parent(s):
241e347
update
Browse files
app.py
CHANGED
@@ -60,7 +60,7 @@ raw_data, original_df = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH
|
|
60 |
# update_collections(original_df.copy())
|
61 |
leaderboard_df = original_df.copy()
|
62 |
|
63 |
-
plot_df = create_plot_df(create_scores_df(raw_data))
|
64 |
|
65 |
(
|
66 |
finished_eval_queue_df,
|
@@ -251,22 +251,23 @@ with demo:
|
|
251 |
queue=True,
|
252 |
)
|
253 |
|
254 |
-
with gr.TabItem("π Metrics through time", elem_id="llm-benchmark-tab-table", id=4):
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
|
|
270 |
with gr.TabItem("π About", elem_id="llm-benchmark-tab-table", id=2):
|
271 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
272 |
|
|
|
60 |
# update_collections(original_df.copy())
|
61 |
leaderboard_df = original_df.copy()
|
62 |
|
63 |
+
# plot_df = create_plot_df(create_scores_df(raw_data))
|
64 |
|
65 |
(
|
66 |
finished_eval_queue_df,
|
|
|
251 |
queue=True,
|
252 |
)
|
253 |
|
254 |
+
# with gr.TabItem("π Metrics through time", elem_id="llm-benchmark-tab-table", id=4):
|
255 |
+
# with gr.Row():
|
256 |
+
# with gr.Column():
|
257 |
+
# chart = create_metric_plot_obj(
|
258 |
+
# plot_df,
|
259 |
+
# [AutoEvalColumn.average.name],
|
260 |
+
# title="Average of Top Scores and Human Baseline Over Time (from last update)",
|
261 |
+
# )
|
262 |
+
# gr.Plot(value=chart, min_width=500)
|
263 |
+
# with gr.Column():
|
264 |
+
# chart = create_metric_plot_obj(
|
265 |
+
# plot_df,
|
266 |
+
# BENCHMARK_COLS,
|
267 |
+
# title="Top Scores and Human Baseline Over Time (from last update)",
|
268 |
+
# )
|
269 |
+
# gr.Plot(value=chart, min_width=500)
|
270 |
+
|
271 |
with gr.TabItem("π About", elem_id="llm-benchmark-tab-table", id=2):
|
272 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
273 |
|