.

Signed-off-by: Jonathan Bnayahu <[email protected]>

app.py

@@ -30,11 +30,12 @@ LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, COLS, BENCHMARK_COLS)
 def init_leaderboard(dataframe):
     if dataframe is None or dataframe.empty:
         raise ValueError("Leaderboard DataFrame is empty or None.")
+    
     return Leaderboard(
         value=dataframe,
         datatype=[c.type for c in fields(AutoEvalColumn)],
         search_columns=[AutoEvalColumn.model.name],
-        interactive=False,
+        interactive=False
     )
 
 def download_csv():
@@ -42,15 +43,15 @@ def download_csv():
         LEADERBOARD_DF.to_csv(buffer, index=False)
         return buffer.getvalue()
 
-demo = gr.Blocks(css=custom_css)
-with demo:
+gui = gr.Blocks(css=custom_css)
+with gui:
     gr.HTML(TITLE_IMAGE)
     gr.HTML(TITLE)
     gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
-            leaderboard = init_leaderboard(LEADERBOARD_DF)
+            leaderboard = init_leaderboard(LEADERBOARD_DF.style.highlight_max(color = 'lightgreen', axis=0).data)
 
         with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
             gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
@@ -82,4 +83,4 @@ with demo:
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+gui.queue(default_concurrency_limit=40).launch()

src/display/utils.py

@@ -25,23 +25,13 @@ auto_eval_column_dict = []
 # Init
 auto_eval_column_dict.append(["model", ColumnContent, ColumnContent("Model", "markdown", True, never_hidden=True)])
 #Scores
-auto_eval_column_dict.append(["average", ColumnContent, ColumnContent("Average ⬆️", "number", True)])
+auto_eval_column_dict.append(["average", ColumnContent, ColumnContent("Average", "number", True)])
 for task in Tasks:
     auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
 
 # We use make dataclass to dynamically fill the scores from Tasks
 AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
 
-## For the queue columns in the submission tab
-@dataclass(frozen=True)
-class EvalQueueColumn:  # Queue column
-    model = ColumnContent("model", "markdown", True)
-    revision = ColumnContent("revision", "str", True)
-    private = ColumnContent("private", "bool", True)
-    precision = ColumnContent("precision", "str", True)
-    weight_type = ColumnContent("weight_type", "str", "Original")
-    status = ColumnContent("status", "str", True)
-
 ## All the model information that we might need
 @dataclass
 class ModelDetails:
@@ -52,8 +42,5 @@ class ModelDetails:
 # Column selection
 COLS = [c.name for c in fields(AutoEvalColumn) if not c.hidden]
 
-EVAL_COLS = [c.name for c in fields(EvalQueueColumn)]
-EVAL_TYPES = [c.type for c in fields(EvalQueueColumn)]
-
 BENCHMARK_COLS = [t.value.col_name for t in Tasks]