add n-shot param

src/display/utils.py

@@ -40,6 +40,7 @@ auto_eval_column_dict.append(["params", ColumnContent, ColumnContent("#Params (B
 auto_eval_column_dict.append(["likes", ColumnContent, ColumnContent("Hub ❤️", "number", False)])
 auto_eval_column_dict.append(["still_on_hub", ColumnContent, ColumnContent("Available on the hub", "bool", False)])
 auto_eval_column_dict.append(["revision", ColumnContent, ColumnContent("Model sha", "str", False, False)])
+auto_eval_column_dict.append(["n_shot", ColumnContent, ColumnContent("n_shot", "number", False)])
 # Dummy column for the search bar (hidden by the custom CSS)
 auto_eval_column_dict.append(["dummy", ColumnContent, ColumnContent("model_name_for_query", "str", False, dummy=True)])
 

src/leaderboard/read_evals.py

@@ -31,6 +31,7 @@ class EvalResult:
     num_params: int = 0
     date: str = "" # submission date of request file
     still_on_hub: bool = False
+    n_shot: int = 0
 
     @classmethod
     def init_from_json_file(self, json_filepath, n_shot_num):
@@ -90,7 +91,8 @@ class EvalResult:
             precision=precision,  
             revision= config.get("model_sha", ""),
             still_on_hub=still_on_hub,
-            architecture=architecture
+            architecture=architecture,
+            n_shot=n_shot_num
         )
 
     def update_with_request_file(self, requests_path):
@@ -200,7 +202,10 @@ class EvalResult:
         except KeyError:
             print(f"Could not find still on hub")
 
-
+        try:
+            data_dict[AutoEvalColumn.n_shot.name] = self.n_shot
+        except KeyError:
+            print(f"Could not find still on hub")
 
         for task in Tasks:
             try:

src/populate.py

@@ -17,9 +17,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced
-    print('X1', df)
     df2 = df[has_no_nan_values(df, benchmark_cols)]
-    print('X2', df2)
     return raw_data, df