from dotenv import load_dotenv load_dotenv() import gradio as gr from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns from apscheduler.schedulers.background import BackgroundScheduler from huggingface_hub import snapshot_download import threading 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 from src.evaluator.run_evaluator import evaluator_runner def restart_space(): try: print("Restarting space...") space_runtime = API.restart_space(repo_id=REPO_ID,token=TOKEN) print(f"Space restarted successfully: {space_runtime}") except Exception as e: print(f"Error restarting space: {str(e)}") try: print("Attempting to download datasets again...") snapshot_download( repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN, force_download=True ) snapshot_download( repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN, force_download=True ) except Exception as download_error: print(f"Error downloading datasets: {str(download_error)}") def init_leaderboard(dataframe): if dataframe is None: 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, ) # API.delete_files(repo_id=QUEUE_REPO, token=TOKEN,delete_patterns=["*"],commit_message="Clearing queue",repo_type="dataset") # API.delete_files(repo_id=RESULTS_REPO, token=TOKEN,delete_patterns=["*"],commit_message="Clearing results",repo_type="dataset") # sys.exit(0) ### Space initialisation try: print(f"\n=== Starting space initialization ===") print(f"EVAL_REQUESTS_PATH: {EVAL_REQUESTS_PATH}") print(f"EVAL_RESULTS_PATH: {EVAL_RESULTS_PATH}") print(f"QUEUE_REPO: {QUEUE_REPO}") print(f"RESULTS_REPO: {RESULTS_REPO}") print(f"TOKEN: {bool(TOKEN)}") print("\n=== Downloading request files ===") snapshot_download( repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN,force_download=True ) print("\n=== Downloading results files ===") snapshot_download( repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN,force_download=True ) print("\n=== Loading leaderboard data ===") LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS) print(f"Leaderboard DataFrame shape: {LEADERBOARD_DF.shape if LEADERBOARD_DF is not None else 'None'}") print("\n=== Loading evaluation queue data ===") finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS) print(f"Finished eval queue shape: {finished_eval_queue_df.shape if finished_eval_queue_df is not None else 'None'}") print(f"Running eval queue shape: {running_eval_queue_df.shape if running_eval_queue_df is not None else 'None'}") print(f"Pending eval queue shape: {pending_eval_queue_df.shape if pending_eval_queue_df is not None else 'None'}") except Exception as e: print(f"\n=== Error during space initialization ===") print(f"Error: {str(e)}") 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) demo = gr.Blocks(css=custom_css) 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(INTRODUCTION_TEXT) gr.Markdown(LLM_BENCHMARKS_TEXT) gr.Markdown(EVALUATION_QUEUE_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(): print(running_eval_queue_df) 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, ) 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, ) scheduler = BackgroundScheduler() scheduler.add_job(restart_space, "interval", seconds=120) thread = threading.Thread(target=evaluator_runner) scheduler.start() thread.start() demo.queue(default_concurrency_limit=40).launch()