change leaderboard and submit

app.py

@@ -27,176 +27,180 @@ from src.display.utils import (
 )
 from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, TOKEN, QUEUE_REPO, REPO_ID, RESULTS_REPO
 from src.populate import get_evaluation_queue_df, get_leaderboard_df
-from src.submission.submit import add_new_eval
+from src.submission.submit import add_new_eval, upload_file
 
 
 def restart_space():
     API.restart_space(repo_id=REPO_ID, token=TOKEN)
 
-try:
-    print(EVAL_REQUESTS_PATH)
-    snapshot_download(
-        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30
-    )
-except Exception:
-    restart_space()
-try:
-    print(EVAL_RESULTS_PATH)
-    snapshot_download(
-        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30
-    )
-except Exception:
-    restart_space()
+# try:
+#     print(EVAL_REQUESTS_PATH)
+#     snapshot_download(
+#         repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30
+#     )
+# except Exception:
+#     restart_space()
+# try:
+#     print(EVAL_RESULTS_PATH)
+#     snapshot_download(
+#         repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30
+#     )
+# except Exception:
+#     restart_space()
 
 
 raw_data, original_df = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
+value=[ c.name for c in fields(AutoEvalColumn) 
+       if c.displayed_by_default and not c.hidden and not c.never_hidden]
+                        
+
 leaderboard_df = original_df.copy()
 
-(
-    finished_eval_queue_df,
-    running_eval_queue_df,
-    pending_eval_queue_df,
-) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
+# (
+#     finished_eval_queue_df,
+#     running_eval_queue_df,
+#     pending_eval_queue_df,
+# ) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
 
 
 # Searching and filtering
-def update_table(
-    hidden_df: pd.DataFrame,
-    columns: list,
-    type_query: list,
-    precision_query: str,
-    size_query: list,
-    show_deleted: bool,
-    query: str,
-):
-    filtered_df = filter_models(hidden_df, type_query, size_query, precision_query, show_deleted)
-    filtered_df = filter_queries(query, filtered_df)
-    df = select_columns(filtered_df, columns)
-    return df
-
-
-def search_table(df: pd.DataFrame, query: str) -> pd.DataFrame:
-    return df[(df[AutoEvalColumn.dummy.name].str.contains(query, case=False))]
-
-
-def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
-    always_here_cols = [
-        AutoEvalColumn.model_type_symbol.name,
-        AutoEvalColumn.model.name,
-    ]
-    # We use COLS to maintain sorting
-    filtered_df = df[
-        always_here_cols + [c for c in COLS if c in df.columns and c in columns] + [AutoEvalColumn.dummy.name]
-    ]
-    return filtered_df
-
-
-def filter_queries(query: str, filtered_df: pd.DataFrame) -> pd.DataFrame:
-    final_df = []
-    if query != "":
-        queries = [q.strip() for q in query.split(";")]
-        for _q in queries:
-            _q = _q.strip()
-            if _q != "":
-                temp_filtered_df = search_table(filtered_df, _q)
-                if len(temp_filtered_df) > 0:
-                    final_df.append(temp_filtered_df)
-        if len(final_df) > 0:
-            filtered_df = pd.concat(final_df)
-            filtered_df = filtered_df.drop_duplicates(
-                subset=[AutoEvalColumn.model.name, AutoEvalColumn.precision.name, AutoEvalColumn.revision.name]
-            )
-
-    return filtered_df
-
-
-def filter_models(
-    df: pd.DataFrame, type_query: list, size_query: list, precision_query: list, show_deleted: bool
-) -> pd.DataFrame:
-    # Show all models
-    if show_deleted:
-        filtered_df = df
-    else:  # Show only still on the hub models
-        filtered_df = df[df[AutoEvalColumn.still_on_hub.name] == True]
-
-    type_emoji = [t[0] for t in type_query]
-    filtered_df = filtered_df.loc[df[AutoEvalColumn.model_type_symbol.name].isin(type_emoji)]
-    filtered_df = filtered_df.loc[df[AutoEvalColumn.precision.name].isin(precision_query + ["None"])]
-
-    numeric_interval = pd.IntervalIndex(sorted([NUMERIC_INTERVALS[s] for s in size_query]))
-    params_column = pd.to_numeric(df[AutoEvalColumn.params.name], errors="coerce")
-    mask = params_column.apply(lambda x: any(numeric_interval.contains(x)))
-    filtered_df = filtered_df.loc[mask]
-
-    return filtered_df
-
-
+# def update_table(
+#     hidden_df: pd.DataFrame,
+#     columns: list,
+#     type_query: list,
+#     precision_query: str,
+#     size_query: list,
+#     show_deleted: bool,
+#     query: str,
+# ):
+#     filtered_df = filter_models(hidden_df, type_query, size_query, precision_query, show_deleted)
+#     filtered_df = filter_queries(query, filtered_df)
+#     df = select_columns(filtered_df, columns)
+#     return df
+
+
+# def search_table(df: pd.DataFrame, query: str) -> pd.DataFrame:
+#     return df[(df[AutoEvalColumn.dummy.name].str.contains(query, case=False))]
+
+
+# def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
+#     always_here_cols = [
+#         AutoEvalColumn.model_type_symbol.name,
+#         AutoEvalColumn.model.name,
+#     ]
+#     # We use COLS to maintain sorting
+#     filtered_df = df[
+#         always_here_cols + [c for c in COLS if c in df.columns and c in columns] + [AutoEvalColumn.dummy.name]
+#     ]
+#     return filtered_df
+
+
+# def filter_queries(query: str, filtered_df: pd.DataFrame) -> pd.DataFrame:
+#     final_df = []
+#     if query != "":
+#         queries = [q.strip() for q in query.split(";")]
+#         for _q in queries:
+#             _q = _q.strip()
+#             if _q != "":
+#                 temp_filtered_df = search_table(filtered_df, _q)
+#                 if len(temp_filtered_df) > 0:
+#                     final_df.append(temp_filtered_df)
+#         if len(final_df) > 0:
+#             filtered_df = pd.concat(final_df)
+#             filtered_df = filtered_df.drop_duplicates(
+#                 subset=[AutoEvalColumn.model.name, AutoEvalColumn.precision.name, AutoEvalColumn.revision.name]
+#             )
+
+#     return filtered_df
+
+
+# def filter_models(
+#     df: pd.DataFrame, type_query: list, size_query: list, precision_query: list, show_deleted: bool
+# ) -> pd.DataFrame:
+#     # Show all models
+#     if show_deleted:
+#         filtered_df = df
+#     else:  # Show only still on the hub models
+#         filtered_df = df[df[AutoEvalColumn.still_on_hub.name] == True]
+
+#     type_emoji = [t[0] for t in type_query]
+#     filtered_df = filtered_df.loc[df[AutoEvalColumn.model_type_symbol.name].isin(type_emoji)]
+#     filtered_df = filtered_df.loc[df[AutoEvalColumn.precision.name].isin(precision_query + ["None"])]
+
+#     numeric_interval = pd.IntervalIndex(sorted([NUMERIC_INTERVALS[s] for s in size_query]))
+#     params_column = pd.to_numeric(df[AutoEvalColumn.params.name], errors="coerce")
+#     mask = params_column.apply(lambda x: any(numeric_interval.contains(x)))
+#     filtered_df = filtered_df.loc[mask]
+
+#     return filtered_df
+
+
+# print([c.name for c in fields(AutoEvalColumn) if c.never_hidden])
 demo = gr.Blocks(css=custom_css)
 with demo:
     gr.HTML(TITLE)
-    gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
+    # 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):
-            with gr.Row():
-                with gr.Column():
-                    with gr.Row():
-                        search_bar = gr.Textbox(
-                            placeholder=" 🔍 Search for your model (separate multiple queries with `;`) and press ENTER...",
-                            show_label=False,
-                            elem_id="search-bar",
-                        )
-                    with gr.Row():
-                        shown_columns = gr.CheckboxGroup(
-                            choices=[
-                                c.name
-                                for c in fields(AutoEvalColumn)
-                                if not c.hidden and not c.never_hidden and not c.dummy
-                            ],
-                            value=[
-                                c.name
-                                for c in fields(AutoEvalColumn)
-                                if c.displayed_by_default and not c.hidden and not c.never_hidden
-                            ],
-                            label="Select columns to show",
-                            elem_id="column-select",
-                            interactive=True,
-                        )
-                    with gr.Row():
-                        deleted_models_visibility = gr.Checkbox(
-                            value=False, label="Show gated/private/deleted models", interactive=True
-                        )
-                with gr.Column(min_width=320):
-                    #with gr.Box(elem_id="box-filter"):
-                    filter_columns_type = gr.CheckboxGroup(
-                        label="Model types",
-                        choices=[t.to_str() for t in ModelType],
-                        value=[t.to_str() for t in ModelType],
-                        interactive=True,
-                        elem_id="filter-columns-type",
-                    )
-                    filter_columns_precision = gr.CheckboxGroup(
-                        label="Precision",
-                        choices=[i.value.name for i in Precision],
-                        value=[i.value.name for i in Precision],
-                        interactive=True,
-                        elem_id="filter-columns-precision",
-                    )
-                    filter_columns_size = gr.CheckboxGroup(
-                        label="Model sizes (in billions of parameters)",
-                        choices=list(NUMERIC_INTERVALS.keys()),
-                        value=list(NUMERIC_INTERVALS.keys()),
-                        interactive=True,
-                        elem_id="filter-columns-size",
-                    )
+            # with gr.Row():
+            #     with gr.Column():
+            #         with gr.Row():
+            #             search_bar = gr.Textbox(
+            #                 placeholder=" 🔍 Search for your model (separate multiple queries with `;`) and press ENTER...",
+            #                 show_label=False,
+            #                 elem_id="search-bar",
+            #             )
+            #         with gr.Row():
+            #             shown_columns = gr.CheckboxGroup(
+            #                 choices=[
+            #                     c.name
+            #                     for c in fields(AutoEvalColumn)
+            #                     if not c.hidden and not c.never_hidden and not c.dummy
+            #                 ],
+                            # value=[
+                            #     c.name
+                            #     for c in fields(AutoEvalColumn)
+                            #     if c.displayed_by_default and not c.hidden and not c.never_hidden
+                            # ],
+            #                 label="Select columns to show",
+            #                 elem_id="column-select",
+            #                 interactive=True,
+            #             )
+            #         with gr.Row():
+            #             deleted_models_visibility = gr.Checkbox(
+            #                 value=False, label="Show gated/private/deleted models", interactive=True
+            #             )
+            #     with gr.Column(min_width=320):
+            #         #with gr.Box(elem_id="box-filter"):
+            #         filter_columns_type = gr.CheckboxGroup(
+            #             label="Model types",
+            #             choices=[t.to_str() for t in ModelType],
+            #             value=[t.to_str() for t in ModelType],
+            #             interactive=True,
+            #             elem_id="filter-columns-type",
+            #         )
+            #         filter_columns_precision = gr.CheckboxGroup(
+            #             label="Precision",
+            #             choices=[i.value.name for i in Precision],
+            #             value=[i.value.name for i in Precision],
+            #             interactive=True,
+            #             elem_id="filter-columns-precision",
+            #         )
+            #         filter_columns_size = gr.CheckboxGroup(
+            #             label="Model sizes (in billions of parameters)",
+            #             choices=list(NUMERIC_INTERVALS.keys()),
+            #             value=list(NUMERIC_INTERVALS.keys()),
+            #             interactive=True,
+            #             elem_id="filter-columns-size",
+            #         )
 
             leaderboard_table = gr.components.Dataframe(
                 value=leaderboard_df[
-                    [c.name for c in fields(AutoEvalColumn) if c.never_hidden]
-                    + shown_columns.value
+                    [c.name for c in fields(AutoEvalColumn) if c.never_hidden] + value
                     + [AutoEvalColumn.dummy.name]
                 ],
-                headers=[c.name for c in fields(AutoEvalColumn) if c.never_hidden] + shown_columns.value,
+                headers=[c.name for c in fields(AutoEvalColumn) if c.never_hidden]  + value,
                 datatype=TYPES,
                 elem_id="leaderboard-table",
                 interactive=False,
@@ -211,34 +215,34 @@ with demo:
                 datatype=TYPES,
                 visible=False,
             )
-            search_bar.submit(
-                update_table,
-                [
-                    hidden_leaderboard_table_for_search,
-                    shown_columns,
-                    filter_columns_type,
-                    filter_columns_precision,
-                    filter_columns_size,
-                    deleted_models_visibility,
-                    search_bar,
-                ],
-                leaderboard_table,
-            )
-            for selector in [shown_columns, filter_columns_type, filter_columns_precision, filter_columns_size, deleted_models_visibility]:
-                selector.change(
-                    update_table,
-                    [
-                        hidden_leaderboard_table_for_search,
-                        shown_columns,
-                        filter_columns_type,
-                        filter_columns_precision,
-                        filter_columns_size,
-                        deleted_models_visibility,
-                        search_bar,
-                    ],
-                    leaderboard_table,
-                    queue=True,
-                )
+            # search_bar.submit(
+            #     update_table,
+            #     [
+            #         hidden_leaderboard_table_for_search,
+            #         shown_columns,
+            #         filter_columns_type,
+            #         filter_columns_precision,
+            #         filter_columns_size,
+            #         deleted_models_visibility,
+            #         search_bar,
+            #     ],
+            #     leaderboard_table,
+            # )
+            # for selector in [shown_columns, filter_columns_type, filter_columns_precision, filter_columns_size, deleted_models_visibility]:
+            #     selector.change(
+            #         update_table,
+            #         [
+            #             hidden_leaderboard_table_for_search,
+            #             shown_columns,
+            #             filter_columns_type,
+            #             filter_columns_precision,
+            #             filter_columns_size,
+            #             deleted_models_visibility,
+            #             search_bar,
+            #         ],
+            #         leaderboard_table,
+            #         queue=True,
+            #     )
 
         with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
             gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
@@ -248,87 +252,88 @@ with demo:
                 with gr.Row():
                     gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
 
-                with gr.Column():
-                    with gr.Accordion(
-                        f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            finished_eval_table = gr.components.Dataframe(
-                                value=finished_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-                    with gr.Accordion(
-                        f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            running_eval_table = gr.components.Dataframe(
-                                value=running_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-
-                    with gr.Accordion(
-                        f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            pending_eval_table = gr.components.Dataframe(
-                                value=pending_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
+                # with gr.Column():
+                #     with gr.Accordion(
+                #         f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
+                #         open=False,
+                #     ):
+                #         with gr.Row():
+                #             finished_eval_table = gr.components.Dataframe(
+                #                 value=finished_eval_queue_df,
+                #                 headers=EVAL_COLS,
+                #                 datatype=EVAL_TYPES,
+                #                 row_count=5,
+                #             )
+                #     with gr.Accordion(
+                #         f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
+                #         open=False,
+                #     ):
+                #         with gr.Row():
+                #             running_eval_table = gr.components.Dataframe(
+                #                 value=running_eval_queue_df,
+                #                 headers=EVAL_COLS,
+                #                 datatype=EVAL_TYPES,
+                #                 row_count=5,
+                #             )
+
+                #     with gr.Accordion(
+                #         f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
+                #         open=False,
+                #     ):
+                #         with gr.Row():
+                #             pending_eval_table = gr.components.Dataframe(
+                #                 value=pending_eval_queue_df,
+                #                 headers=EVAL_COLS,
+                #                 datatype=EVAL_TYPES,
+                #                 row_count=5,
+                #             )
             with gr.Row():
-                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
+                gr.Markdown("# ✉️✨ Submit your files here!", elem_classes="markdown-text")
 
             with gr.Row():
-                with gr.Column():
-                    model_name_textbox = gr.Textbox(label="Model name")
-                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
-                    model_type = gr.Dropdown(
-                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
-                        label="Model type",
-                        multiselect=False,
-                        value=None,
-                        interactive=True,
-                    )
-
-                with gr.Column():
-                    precision = gr.Dropdown(
-                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
-                        label="Precision",
-                        multiselect=False,
-                        value="float16",
-                        interactive=True,
-                    )
-                    weight_type = gr.Dropdown(
-                        choices=[i.value.name for i in WeightType],
-                        label="Weights type",
-                        multiselect=False,
-                        value="Original",
-                        interactive=True,
-                    )
-                    base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
-
-            submit_button = gr.Button("Submit Eval")
-            submission_result = gr.Markdown()
-            submit_button.click(
-                add_new_eval,
-                [
-                    model_name_textbox,
-                    base_model_name_textbox,
-                    revision_name_textbox,
-                    precision,
-                    weight_type,
-                    model_type,
-                ],
-                submission_result,
-            )
+                upload = gr.Interface(fn=upload_file,inputs="file" ,outputs=None)
+                # with gr.Column():
+                #     model_name_textbox = gr.Textbox(label="Model name")
+                #     revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
+                #     model_type = gr.Dropdown(
+                #         choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
+                #         label="Model type",
+                #         multiselect=False,
+                #         value=None,
+                #         interactive=True,
+                #     )
+
+                # with gr.Column():
+                #     precision = gr.Dropdown(
+                #         choices=[i.value.name for i in Precision if i != Precision.Unknown],
+                #         label="Precision",
+                #         multiselect=False,
+                #         value="float16",
+                #         interactive=True,
+                #     )
+                #     weight_type = gr.Dropdown(
+                #         choices=[i.value.name for i in WeightType],
+                #         label="Weights type",
+                #         multiselect=False,
+                #         value="Original",
+                #         interactive=True,
+                #     )
+                #     base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
+
+            # submit_button = gr.Button("Submit Eval")
+            # submission_result = gr.Markdown()
+            # submit_button.click(
+            #     add_new_eval,
+            #     [
+            #         model_name_textbox,
+            #         base_model_name_textbox,
+            #         revision_name_textbox,
+            #         precision,
+            #         weight_type,
+            #         model_type,
+            #     ],
+            #     submission_result,
+            # )
 
     with gr.Row():
         with gr.Accordion("📙 Citation", open=False):
@@ -341,6 +346,7 @@ with demo:
             )
 
 scheduler = BackgroundScheduler()
-scheduler.add_job(restart_space, "interval", seconds=1800)
+scheduler.add_job(restart_space, "interval", seconds=30)
 scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+
+demo.queue(default_concurrency_limit=40).launch()

src/display/about.py

@@ -16,7 +16,7 @@ class Tasks(Enum):
 
 
 # Your leaderboard name
-TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
+TITLE = """<h1 align="center" id="space-title">OPENT2T LEADERBOARD</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """

src/display/utils.py

@@ -31,15 +31,15 @@ auto_eval_column_dict.append(["average", ColumnContent, ColumnContent("Average
 for task in Tasks:
     auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
 # Model information
-auto_eval_column_dict.append(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
-auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
-auto_eval_column_dict.append(["weight_type", ColumnContent, ColumnContent("Weight type", "str", False, True)])
-auto_eval_column_dict.append(["precision", ColumnContent, ColumnContent("Precision", "str", False)])
-auto_eval_column_dict.append(["license", ColumnContent, ColumnContent("Hub License", "str", False)])
-auto_eval_column_dict.append(["params", ColumnContent, ColumnContent("#Params (B)", "number", False)])
-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(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
+# auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
+# auto_eval_column_dict.append(["weight_type", ColumnContent, ColumnContent("Weight type", "str", False, True)])
+# auto_eval_column_dict.append(["precision", ColumnContent, ColumnContent("Precision", "str", False)])
+# auto_eval_column_dict.append(["license", ColumnContent, ColumnContent("Hub License", "str", False)])
+# auto_eval_column_dict.append(["params", ColumnContent, ColumnContent("#Params (B)", "number", False)])
+# 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)])
 # 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

@@ -23,12 +23,12 @@ class EvalResult:
     precision: Precision = Precision.Unknown
     model_type: ModelType = ModelType.Unknown # Pretrained, fine tuned, ...
     weight_type: WeightType = WeightType.Original # Original or Adapter
-    architecture: str = "Unknown" 
+    # architecture: str = "Unknown" 
     license: str = "?"
     likes: int = 0
     num_params: int = 0
     date: str = "" # submission date of request file
-    still_on_hub: bool = False
+    # still_on_hub: bool = False
 
     @classmethod
     def init_from_json_file(self, json_filepath):
@@ -38,7 +38,7 @@ class EvalResult:
 
         config = data.get("config")
 
-        # Precision
+        # # Precision
         precision = Precision.from_str(config.get("model_dtype"))
 
         # Get model and org
@@ -55,14 +55,14 @@ class EvalResult:
             result_key = f"{org}_{model}_{precision.value.name}"
         full_model = "/".join(org_and_model)
 
-        still_on_hub, _, model_config = is_model_on_hub(
-            full_model, config.get("model_sha", "main"), trust_remote_code=True, test_tokenizer=False
-        )
-        architecture = "?"
-        if model_config is not None:
-            architectures = getattr(model_config, "architectures", None)
-            if architectures:
-                architecture = ";".join(architectures)
+        # still_on_hub, _, model_config = is_model_on_hub(
+        #     full_model, config.get("model_sha", "main"), trust_remote_code=True, test_tokenizer=False
+        # )
+        # architecture = "?"
+        # if model_config is not None:
+        #     architectures = getattr(model_config, "architectures", None)
+        #     if architectures:
+        #         architecture = ";".join(architectures)
 
         # Extract results available in this file (some results are split in several files)
         results = {}
@@ -85,8 +85,8 @@ class EvalResult:
             results=results,
             precision=precision,  
             revision= config.get("model_sha", ""),
-            still_on_hub=still_on_hub,
-            architecture=architecture
+            # still_on_hub=still_on_hub,
+            # architecture=architecture
         )
 
     def update_with_request_file(self, requests_path):
@@ -110,19 +110,19 @@ class EvalResult:
         average = sum([v for v in self.results.values() if v is not None]) / len(Tasks)
         data_dict = {
             "eval_name": self.eval_name,  # not a column, just a save name,
-            AutoEvalColumn.precision.name: self.precision.value.name,
-            AutoEvalColumn.model_type.name: self.model_type.value.name,
+            # AutoEvalColumn.precision.name: self.precision.value.name,
+            # AutoEvalColumn.model_type.name: self.model_type.value.name,
             AutoEvalColumn.model_type_symbol.name: self.model_type.value.symbol,
-            AutoEvalColumn.weight_type.name: self.weight_type.value.name,
-            AutoEvalColumn.architecture.name: self.architecture,
+            # AutoEvalColumn.weight_type.name: self.weight_type.value.name,
+            # AutoEvalColumn.architecture.name: self.architecture,
             AutoEvalColumn.model.name: make_clickable_model(self.full_model),
             AutoEvalColumn.dummy.name: self.full_model,
-            AutoEvalColumn.revision.name: self.revision,
+            # AutoEvalColumn.revision.name: self.revision,
             AutoEvalColumn.average.name: average,
-            AutoEvalColumn.license.name: self.license,
-            AutoEvalColumn.likes.name: self.likes,
-            AutoEvalColumn.params.name: self.num_params,
-            AutoEvalColumn.still_on_hub.name: self.still_on_hub,
+            # AutoEvalColumn.license.name: self.license,
+            # AutoEvalColumn.likes.name: self.likes,
+            # AutoEvalColumn.params.name: self.num_params,
+            # AutoEvalColumn.still_on_hub.name: self.still_on_hub,
         }
 
         for task in Tasks:
@@ -156,8 +156,9 @@ def get_request_file_for_model(requests_path, model_name, precision):
 def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResult]:
     """From the path of the results folder root, extract all needed info for results"""
     model_result_filepaths = []
-
+   
     for root, _, files in os.walk(results_path):
+        print(files)
         # We should only have json files in model results
         if len(files) == 0 or any([not f.endswith(".json") for f in files]):
             continue
@@ -185,6 +186,7 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
             eval_results[eval_name] = eval_result
 
     results = []
+    # print(eval_results)
     for v in eval_results.values():
         try:
             v.to_dict() # we test if the dict version is complete

src/populate.py

@@ -10,10 +10,13 @@ from src.leaderboard.read_evals import get_raw_eval_results
 
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
     raw_data = get_raw_eval_results(results_path, requests_path)
+   
     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)
+    print(df)
+    print(cols)
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced

src/submission/submit.py

@@ -3,7 +3,7 @@ import os
 from datetime import datetime, timezone
 
 from src.display.formatting import styled_error, styled_message, styled_warning
-from src.envs import API, EVAL_REQUESTS_PATH, TOKEN, QUEUE_REPO
+from src.envs import API, EVAL_REQUESTS_PATH, TOKEN, QUEUE_REPO, EVAL_RESULTS_PATH
 from src.submission.check_validity import (
     already_submitted_models,
     check_model_card,
@@ -14,6 +14,32 @@ from src.submission.check_validity import (
 REQUESTED_MODELS = None
 USERS_TO_SUBMISSION_DATES = None
 
+def assert_upload(file_obj):
+    #TODO: assert the acc of file
+    return True
+    pass
+def upload_file(file_obj):
+    flag = assert_upload(file_obj)
+    
+
+    now = datetime.now()
+    timestamp_str = now.strftime("%Y-%m-%dT%H-%M-%S")
+    output_file = "results_"+timestamp_str+".json"
+
+    example = json.load(open(file_obj, "r"))
+    model_name = example["config"]["model_name"]
+    output_dir = os.path.join(EVAL_RESULTS_PATH,model_name)
+    os.makedirs(output_dir, exist_ok=True)
+
+    output_path = os.path.join(output_dir, output_file)
+
+    with open(file_obj, "r") as f:
+        content = f.read()
+    with open(output_path, "w") as f:
+        f.write(content)
+    
+    
+
 def add_new_eval(
     model: str,
     base_model: str,