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 src.about import ( CITATION_BUTTON_LABEL, CITATION_BUTTON_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_RESULTS_PATH_CDM, EVAL_RESULTS_PATH_CDM_FI, REPO_ID, RESULTS_REPO_CDM, RESULTS_REPO_CDM_FI, TOKEN from src.populate import get_leaderboard_df def restart_space(): API.restart_space(repo_id=REPO_ID) ### Space initialisation try: print(EVAL_RESULTS_PATH_CDM) snapshot_download( repo_id=RESULTS_REPO_CDM, local_dir=EVAL_RESULTS_PATH_CDM, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN, ) except Exception: restart_space() try: print(EVAL_RESULTS_PATH_CDM_FI) snapshot_download( repo_id=RESULTS_REPO_CDM_FI, local_dir=EVAL_RESULTS_PATH_CDM_FI, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN, ) except Exception: restart_space() LEADERBOARD_DF_CDM = get_leaderboard_df(EVAL_RESULTS_PATH_CDM, COLS, BENCHMARK_COLS) LEADERBOARD_DF_CDM_FI = get_leaderboard_df(EVAL_RESULTS_PATH_CDM_FI, 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)], 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], # 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.seq_length.name, # type="checkboxgroup", # label="Sequence Lengths", # ) # 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) 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("MIMIC CDM", elem_id="llm-benchmark-tab-table", id=0): leaderboard = init_leaderboard(LEADERBOARD_DF_CDM) with gr.TabItem("MIMIC CDM FI", elem_id="llm-benchmark-tab-table", id=1): leaderboard = init_leaderboard(LEADERBOARD_DF_CDM_FI) with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2): gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-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, ) scheduler = BackgroundScheduler() scheduler.add_job(restart_space, "interval", seconds=1800) scheduler.start() demo.queue(default_concurrency_limit=40).launch(share=True)