test

README.md

@@ -41,4 +41,7 @@ If you encounter problem on the space, don't hesitate to restart it to remove th
 You'll find 
 - the main table' columns names and properties in `src/display/utils.py`
 - the logic to read all results and request files, then convert them in dataframe lines, in `src/leaderboard/read_evals.py`, and `src/populate.py`
-- the logic to allow or filter submissions in `src/submission/submit.py` and `src/submission/check_validity.py`
+- the logic to allow or filter submissions in `src/submission/submit.py` and `src/submission/check_validity.py`
+
+
+src.display.util 负责按钮选项（打勾区域）

app.py

@@ -96,6 +96,7 @@ with demo:
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
+            #TODO
             leaderboard = init_leaderboard(LEADERBOARD_DF)
 
         with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):

src/about.py

@@ -10,6 +10,7 @@ class Task:
 
 # Select your tasks here
 # ---------------------------------------------------
+#TODO 指标
 class Tasks(Enum):
     # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
     task0 = Task("anli_r1", "acc", "ANLI")

src/display/utils.py

@@ -22,6 +22,7 @@ class ColumnContent:
 
 ## Leaderboard columns
 auto_eval_column_dict = []
+#TODO
 # Init
 auto_eval_column_dict.append(["model_type_symbol", ColumnContent, ColumnContent("T", "str", True, never_hidden=True)])
 auto_eval_column_dict.append(["model", ColumnContent, ColumnContent("Model", "markdown", True, never_hidden=True)])

src/populate.py

@@ -14,6 +14,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)
+
     df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
     df = df[cols].round(decimals=2)