just delta abs

app.py

@@ -147,18 +147,16 @@ with demo:
                             show_label=False,
                             elem_id="search-bar",
                         )
-                    with gr.Row():
-                        shown_columns = gr.Radio(
-                            choices=[
-                                c for c in METRICS
-                            ],
-                            value=[
-                                c for c in METRICS
-                            ],
-                            label="Select metrics to show",
-                            elem_id="metrics-select",
-                            interactive=True,
-                        )
+                    # with gr.Row():
+                    #     shown_columns = gr.Radio(
+                    #         choices=[
+                    #             c for c in METRICS
+                    #         ],
+                    #         value=METRICS[0],
+                    #         label="Select metrics to show",
+                    #         elem_id="metrics-select",
+                    #         interactive=True,
+                    #     )
                     with gr.Row():
                         shown_columns = gr.CheckboxGroup(
                             choices=[

src/display/about.py

@@ -12,15 +12,15 @@ class Task:
 class Tasks(Enum):
     # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
     task0 = Task("logiqa", "delta_abs", "LogiQA Δ")
-    task1 = Task("logiqa", "delta_rel", "LogiQA Δ%")
-    task2 = Task("logiqa", "acc_base", "LogiQA Acc")
-    task3 = Task("logiqa", "acc_cot", "LogiQA AccCoT")
+    #task1 = Task("logiqa", "delta_rel", "LogiQA Δ%")
+    #task2 = Task("logiqa", "acc_base", "LogiQA Acc")
+    #task3 = Task("logiqa", "acc_cot", "LogiQA AccCoT")
     task4 = Task("logiqa2", "delta_abs", "LogiQA2 Δ")
-    task5 = Task("logiqa2", "delta_rel", "LogiQA2 Δ%")
-    task6 = Task("logiqa2", "acc_base", "LogiQA2 Acc")
-    task7 = Task("logiqa2", "acc_cot", "LogiQA2 AccCoT")
+    #task5 = Task("logiqa2", "delta_rel", "LogiQA2 Δ%")
+    #task6 = Task("logiqa2", "acc_base", "LogiQA2 Acc")
+    #task7 = Task("logiqa2", "acc_cot", "LogiQA2 AccCoT")
 
-METRICS = list(set([task.value.metric for task in Tasks]))
+#METRICS = list(set([task.value.metric for task in Tasks]))
 
 
 

src/leaderboard/read_evals.py

@@ -84,7 +84,7 @@ class EvalResult:
             model=model,
             results=results,
             precision=precision,  
-            revision= config.get("model_sha", ""),
+            revision=config.get("model_sha", ""),
             still_on_hub=still_on_hub,
             architecture=architecture
         )