next iteration

app.py

@@ -73,14 +73,6 @@ def init_leaderboard(dataframe, track):
         hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
         filter_columns=[
             ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
-            ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
-            ColumnFilter(
-                AutoEvalColumn.params.name,
-                type="slider",
-                min=0.01,
-                max=150,
-                label="Select the number of parameters (B)",
-            ),
             ColumnFilter(
                 AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
             ),

src/leaderboard/read_evals.py

@@ -154,11 +154,6 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
 
     eval_results = {}
     for model_result_filepath in model_result_filepaths:
-        with open(model_result_filepath, 'r') as f:
-            this_track = f["track"]
-            if this_track != track:
-                continue
-
         # Creation of result
         eval_result = EvalResult.init_from_json_file(model_result_filepath)
         eval_result.update_with_request_file(requests_path)

src/populate.py

@@ -14,8 +14,8 @@ 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)
+    # df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
+    df = df[cols].round(decimals=1)
 
     # filter out if any of the benchmarks have not been produced
     df = df[has_no_nan_values(df, benchmark_cols)]