Spaces:
Running
Running
Shiyu Zhao
commited on
Commit
·
be954af
1
Parent(s):
86d5a63
Update space
Browse files- app.py +12 -11
- submissions/ance_test2_tester2/latest.json +0 -6
- submissions/ance_test2_tester2/metadata_20241024_043111.json +0 -21
- submissions/ance_test2_tester2/metadata_20241024_044359.json +0 -21
- submissions/ance_test2_tester2/predictions_20241024_043111.csv +0 -0
- submissions/ance_test2_tester2/predictions_20241024_044359.csv +0 -0
- submissions/ance_test3_tester3/latest.json +0 -6
- submissions/ance_test3_tester3/metadata_20241024_051521.json +0 -21
- submissions/ance_test3_tester3/predictions_20241024_051521.csv +0 -0
- submissions/ance_test_tester1/latest.json +0 -6
- submissions/ance_test_tester1/metadata_20241024_004918.json +0 -20
- submissions/ance_test_tester1/predictions_20241024_004918.csv +0 -0
app.py
CHANGED
@@ -876,7 +876,7 @@ with gr.Blocks(css=css) as demo:
|
|
876 |
gr.Markdown("## Submit Your Results")
|
877 |
gr.Markdown("""
|
878 |
Submit your results to be included in the leaderboard. Please ensure your submission meets all requirements.
|
879 |
-
For questions, contact stark-qa@cs.stanford.edu
|
880 |
""")
|
881 |
|
882 |
with gr.Row():
|
@@ -885,10 +885,6 @@ with gr.Blocks(css=css) as demo:
|
|
885 |
label="Method Name (max 25 chars)*",
|
886 |
placeholder="e.g., MyRetrievalModel-v1"
|
887 |
)
|
888 |
-
team_name = gr.Textbox(
|
889 |
-
label="Team Name (max 25 chars)*",
|
890 |
-
placeholder="e.g., Stanford NLP"
|
891 |
-
)
|
892 |
dataset = gr.Dropdown(
|
893 |
choices=["amazon", "mag", "prime"],
|
894 |
label="Dataset*",
|
@@ -899,6 +895,10 @@ with gr.Blocks(css=css) as demo:
|
|
899 |
label="Split*",
|
900 |
value="test"
|
901 |
)
|
|
|
|
|
|
|
|
|
902 |
contact_email = gr.Textbox(
|
903 |
label="Contact Email(s)*",
|
904 |
placeholder="email@example.com; another@example.com"
|
@@ -909,6 +909,9 @@ with gr.Blocks(css=css) as demo:
|
|
909 |
value="Others",
|
910 |
info="Select the appropriate category for your model"
|
911 |
)
|
|
|
|
|
|
|
912 |
model_description = gr.Textbox(
|
913 |
label="Model Description*",
|
914 |
lines=3,
|
@@ -918,17 +921,15 @@ with gr.Blocks(css=css) as demo:
|
|
918 |
label="Code Repository*",
|
919 |
placeholder="https://github.com/snap-stanford/stark-leaderboard"
|
920 |
)
|
921 |
-
|
922 |
-
|
|
|
|
|
923 |
csv_file = gr.File(
|
924 |
label="Prediction CSV*",
|
925 |
file_types=[".csv"],
|
926 |
type="filepath"
|
927 |
)
|
928 |
-
hardware = gr.Textbox(
|
929 |
-
label="Hardware Specifications*",
|
930 |
-
placeholder="e.g., 4x NVIDIA A100 80GB"
|
931 |
-
)
|
932 |
paper_link = gr.Textbox(
|
933 |
label="Paper Link (Optional)",
|
934 |
placeholder="https://arxiv.org/abs/..."
|
|
|
876 |
gr.Markdown("## Submit Your Results")
|
877 |
gr.Markdown("""
|
878 |
Submit your results to be included in the leaderboard. Please ensure your submission meets all requirements.
|
879 |
+
For questions, contact stark-qa@cs.stanford.edu. Detailed instructions can be referred at [submission instructions](https://docs.google.com/document/d/11coGjTmOEi9p9-PUq1oy0eTOj8f_8CVQhDl5_0FKT14/edit?usp=sharing).
|
880 |
""")
|
881 |
|
882 |
with gr.Row():
|
|
|
885 |
label="Method Name (max 25 chars)*",
|
886 |
placeholder="e.g., MyRetrievalModel-v1"
|
887 |
)
|
|
|
|
|
|
|
|
|
888 |
dataset = gr.Dropdown(
|
889 |
choices=["amazon", "mag", "prime"],
|
890 |
label="Dataset*",
|
|
|
895 |
label="Split*",
|
896 |
value="test"
|
897 |
)
|
898 |
+
team_name = gr.Textbox(
|
899 |
+
label="Team Name (max 25 chars)*",
|
900 |
+
placeholder="e.g., Stanford NLP"
|
901 |
+
)
|
902 |
contact_email = gr.Textbox(
|
903 |
label="Contact Email(s)*",
|
904 |
placeholder="email@example.com; another@example.com"
|
|
|
909 |
value="Others",
|
910 |
info="Select the appropriate category for your model"
|
911 |
)
|
912 |
+
|
913 |
+
|
914 |
+
with gr.Column():
|
915 |
model_description = gr.Textbox(
|
916 |
label="Model Description*",
|
917 |
lines=3,
|
|
|
921 |
label="Code Repository*",
|
922 |
placeholder="https://github.com/snap-stanford/stark-leaderboard"
|
923 |
)
|
924 |
+
hardware = gr.Textbox(
|
925 |
+
label="Hardware Specifications*",
|
926 |
+
placeholder="e.g., 4x NVIDIA A100 80GB"
|
927 |
+
)
|
928 |
csv_file = gr.File(
|
929 |
label="Prediction CSV*",
|
930 |
file_types=[".csv"],
|
931 |
type="filepath"
|
932 |
)
|
|
|
|
|
|
|
|
|
933 |
paper_link = gr.Textbox(
|
934 |
label="Paper Link (Optional)",
|
935 |
placeholder="https://arxiv.org/abs/..."
|
submissions/ance_test2_tester2/latest.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"latest_submission": "20241024_044359",
|
3 |
-
"status": "approved",
|
4 |
-
"method_name": "ance-test2",
|
5 |
-
"team_name": "tester2"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test2_tester2/metadata_20241024_043111.json
DELETED
@@ -1,21 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"Method Name": "ance_test2",
|
3 |
-
"Team Name": "tester2",
|
4 |
-
"Dataset": "amazon",
|
5 |
-
"Split": "human_generated_eval",
|
6 |
-
"Contact Email(s)": "shiyuz@stanford.edu",
|
7 |
-
"Code Repository": "https://github.com/snap-stanford/stark",
|
8 |
-
"Model Description": "test",
|
9 |
-
"Hardware": "a100",
|
10 |
-
"(Optional) Paper link": "",
|
11 |
-
"Model Type": "Others",
|
12 |
-
"results": {
|
13 |
-
"hit@1": 25.93,
|
14 |
-
"hit@5": 54.32,
|
15 |
-
"recall@20": 23.69,
|
16 |
-
"mrr": 37.08
|
17 |
-
},
|
18 |
-
"status": "approved",
|
19 |
-
"submission_date": "2024-10-24 04:32:14",
|
20 |
-
"csv_path": "submissions/ance_test2_tester2/predictions_20241024_043111.csv"
|
21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test2_tester2/metadata_20241024_044359.json
DELETED
@@ -1,21 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"Method Name": "ance-test2",
|
3 |
-
"Team Name": "tester2",
|
4 |
-
"Dataset": "amazon",
|
5 |
-
"Split": "human_generated_eval",
|
6 |
-
"Contact Email(s)": "shiyuz@stanford.edu",
|
7 |
-
"Code Repository": "https://github.com/snap-stanford/stark",
|
8 |
-
"Model Description": "tester2",
|
9 |
-
"Hardware": "a100",
|
10 |
-
"(Optional) Paper link": "",
|
11 |
-
"Model Type": "Others",
|
12 |
-
"results": {
|
13 |
-
"hit@1": 25.93,
|
14 |
-
"hit@5": 54.32,
|
15 |
-
"recall@20": 23.69,
|
16 |
-
"mrr": 37.08
|
17 |
-
},
|
18 |
-
"status": "approved",
|
19 |
-
"submission_date": "2024-10-24 04:44:32",
|
20 |
-
"csv_path": "submissions/ance_test2_tester2/predictions_20241024_044359.csv"
|
21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test2_tester2/predictions_20241024_043111.csv
DELETED
The diff for this file is too large to render.
See raw diff
|
|
submissions/ance_test2_tester2/predictions_20241024_044359.csv
DELETED
The diff for this file is too large to render.
See raw diff
|
|
submissions/ance_test3_tester3/latest.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"latest_submission": "20241024_051521",
|
3 |
-
"status": "approved",
|
4 |
-
"method_name": "ance-test3",
|
5 |
-
"team_name": "tester3"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test3_tester3/metadata_20241024_051521.json
DELETED
@@ -1,21 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"Method Name": "ance-test3",
|
3 |
-
"Team Name": "tester3",
|
4 |
-
"Dataset": "amazon",
|
5 |
-
"Split": "human_generated_eval",
|
6 |
-
"Contact Email(s)": "shiyuz@stanford.edu",
|
7 |
-
"Code Repository": "https://huggingface.co/spaces/snap-stanford/stark-leaderboard",
|
8 |
-
"Model Description": "tester3",
|
9 |
-
"Hardware": "tester3",
|
10 |
-
"(Optional) Paper link": "",
|
11 |
-
"Model Type": "Small Dense Retrievers",
|
12 |
-
"results": {
|
13 |
-
"hit@1": 25.93,
|
14 |
-
"hit@5": 54.32,
|
15 |
-
"recall@20": 23.69,
|
16 |
-
"mrr": 37.08
|
17 |
-
},
|
18 |
-
"status": "approved",
|
19 |
-
"submission_date": "2024-10-24 05:15:52",
|
20 |
-
"csv_path": "submissions/ance_test3_tester3/predictions_20241024_051521.csv"
|
21 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test3_tester3/predictions_20241024_051521.csv
DELETED
The diff for this file is too large to render.
See raw diff
|
|
submissions/ance_test_tester1/latest.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"latest_submission": "20241024_004918",
|
3 |
-
"status": "approved",
|
4 |
-
"method_name": "ance-test",
|
5 |
-
"team_name": "tester1"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test_tester1/metadata_20241024_004918.json
DELETED
@@ -1,20 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"Method Name": "ance-test",
|
3 |
-
"Team Name": "tester1",
|
4 |
-
"Dataset": "amazon",
|
5 |
-
"Split": "human_generated_eval",
|
6 |
-
"Contact Email(s)": "shiyuz@stanford.edu",
|
7 |
-
"Code Repository": "https://github.com/snap-stanford/stark",
|
8 |
-
"Model Description": "tester1",
|
9 |
-
"Hardware": "a100",
|
10 |
-
"(Optional) Paper link": "",
|
11 |
-
"results": {
|
12 |
-
"hit@1": 25.93,
|
13 |
-
"hit@5": 54.32,
|
14 |
-
"recall@20": 23.69,
|
15 |
-
"mrr": 37.08
|
16 |
-
},
|
17 |
-
"status": "approved",
|
18 |
-
"submission_date": "2024-10-24 00:49:49",
|
19 |
-
"csv_path": "submissions/ance_test_tester1/predictions_20241024_004918.csv"
|
20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
submissions/ance_test_tester1/predictions_20241024_004918.csv
DELETED
The diff for this file is too large to render.
See raw diff
|
|