Update app.py

Initial version; without translation subset

app.py

@@ -1,204 +1,136 @@
 import gradio as gr
-from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
 import pandas as pd
-from apscheduler.schedulers.background import BackgroundScheduler
-from huggingface_hub import snapshot_download
+from gradio_leaderboard import Leaderboard, SelectColumns, ColumnFilter
+
+TITLE = "<h1>M-RewardBench Leaderboard</h1>"
+INTRODUCTION_TEXT = "https://m-rewardbench.github.io/"
+GOOGLE_SHEET_URL = "https://docs.google.com/spreadsheets/d/1qrD7plUdrBwAw7G6UeDVZAaV9ihxaNAcoiKwSaqotR4/export?gid=0&format=csv"
+ABOUT_TEXT = """Welcome to M-RewardBench Leaderboard!"""
+
+
+class AutoEvalColumn:
+  model = {
+    "name": "Model",
+    "type": "markdown",
+    "displayed_by_default": True,
+    "never_hidden": True,
+  }
+  
+  model_type = {
+    "name": "Model_Type",
+    "type": "markdown",
+    "displayed_by_default": True,
+    "never_hidden": True,
+  }
+  
+  eng_Latn = {
+    "name": "eng_Latn",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  Avg_Multilingual = {
+    "name": "Avg_Multilingual",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  arb_Arab = {
+    "name": "arb_Arab",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  tur_Latn = {
+    "name": "tur_Latn",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  rus_Cyrl = {
+    "name": "rus_Cyrl",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  ces_Latn = {
+    "name": "ces_Latn",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  pol_Latn = {
+    "name": "pol_Latn",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }
+  
+  kor_Hang = {
+    "name": "kor_Hang",
+    "type": "float",
+    "displayed_by_default": True,
+    "never_hidden": False,
+  }					
+
+
+def get_result_data():
+  return pd.read_csv(GOOGLE_SHEET_URL)
 
-from src.about import (
-    CITATION_BUTTON_LABEL,
-    CITATION_BUTTON_TEXT,
-    EVALUATION_QUEUE_TEXT,
-    INTRODUCTION_TEXT,
-    LLM_BENCHMARKS_TEXT,
-    TITLE,
-)
-from src.display.css_html_js import custom_css
-from src.display.utils import (
-    BENCHMARK_COLS,
-    COLS,
-    EVAL_COLS,
-    EVAL_TYPES,
-    AutoEvalColumn,
-    ModelType,
-    fields,
-    WeightType,
-    Precision
-)
-from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
-from src.populate import get_evaluation_queue_df, get_leaderboard_df
-from src.submission.submit import add_new_eval
-
-
-def restart_space():
-    API.restart_space(repo_id=REPO_ID)
-
-### Space initialisation
-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, token=TOKEN
-    )
-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, token=TOKEN
-    )
-except Exception:
-    restart_space()
-
-
-LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
-
-(
-    finished_eval_queue_df,
-    running_eval_queue_df,
-    pending_eval_queue_df,
-) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_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)],
-        select_columns=SelectColumns(
-            default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
-            cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
-            label="Select Columns to Display:",
-        ),
-        search_columns=[AutoEvalColumn.model.name, AutoEvalColumn.license.name],
-        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
-            ),
-        ],
-        bool_checkboxgroup_label="Hide models",
-        interactive=False,
-    )
-
-
-demo = gr.Blocks(css=custom_css)
+  if dataframe is None or dataframe.empty:
+    raise ValueError("Leaderboard DataFrame is empty or None.")
+
+  return Leaderboard(
+    value=dataframe,
+    datatype=[
+      col["type"]
+      for col in AutoEvalColumn.__dict__.values()
+      if isinstance(col, dict)
+    ],
+    select_columns=SelectColumns(
+      default_selection=[
+        col["name"]
+        for col in AutoEvalColumn.__dict__.values()
+        if isinstance(col, dict) and col["displayed_by_default"]
+      ],
+      cant_deselect=[
+        col["name"]
+        for col in AutoEvalColumn.__dict__.values()
+        if isinstance(col, dict) and col.get("never_hidden", False)
+      ],
+      label="Select Columns to Display:",
+    ),
+    search_columns=["Model"],
+    interactive=False,
+  )
+
+
+def format_model_link(row):
+  """Format model name as HTML link if URL is available"""
+  model_name = row["Model"]
+  # url = row.get("URL", "")
+  # if pd.notna(url) and url.strip():
+  #   return f'<a href="{url}" target="_blank">{model_name}</a>'
+  return model_name
+
+
+demo = gr.Blocks()
 with demo:
-    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)
-
-        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
-            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
-
-        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
-            with gr.Column():
-                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.Row():
-                gr.Markdown("# ✉️✨ Submit your model 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,
-            )
+  gr.HTML(TITLE)
+  gr.Markdown(INTRODUCTION_TEXT)
 
-    with gr.Row():
-        with gr.Accordion("📙 Citation", open=False):
-            citation_button = gr.Textbox(
-                value=CITATION_BUTTON_TEXT,
-                label=CITATION_BUTTON_LABEL,
-                lines=20,
-                elem_id="citation-button",
-                show_copy_button=True,
-            )
+  with gr.Tabs() as tabs:
+    with gr.TabItem("🏅 Leaderboard"):
+      df = get_result_data()
+      df["Model"] = df.apply(format_model_link, axis=1)
+      leaderboard = init_leaderboard(df)
 
-scheduler = BackgroundScheduler()
-scheduler.add_job(restart_space, "interval", seconds=1800)
-scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+demo.launch()