import os import shutil import gradio as gr from pathlib import Path 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, EVALUATION_QUEUE_TEXT, INTRODUCTION_TEXT, LLM_BENCHMARKS_TEXT, TITLE, Detail_Tasks, ) 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) LEADERBOARD_DF_N_CORRECT = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS, version="n_correct") LEADERBOARD_DF_1_CORRECT_VAR = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS, version="1_correct_var") ( 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.") print(dataframe.columns) 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 and c.name in dataframe.columns], cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden and c.name in dataframe.columns], label="Select Columns to Display:", ), search_columns=[AutoEvalColumn.model.name], hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden and c.name in dataframe.columns], filter_columns=[ ColumnFilter(AutoEvalColumn.output_format.name, type="checkboxgroup", label="Output Format"), ], interactive=False, ) # def upload_file(file): # UPLOAD_FOLDER = "./data" # if not os.path.exists(UPLOAD_FOLDER): # os.mkdir(UPLOAD_FOLDER) # shutil.copy(file, UPLOAD_FOLDER) # gr.Info("File Uploaded!!!") 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("🏅 1 Correct", elem_id="llm-benchmark-tab-table", id=0): leaderboard = init_leaderboard(LEADERBOARD_DF) with gr.TabItem("🏅 1 Correct + Variations", elem_id="llm-benchmark-tab-table", id=4): leaderboard = init_leaderboard(LEADERBOARD_DF_1_CORRECT_VAR) with gr.TabItem("🏅 N Correct", elem_id="llm-benchmark-tab-table", id=1): leaderboard = init_leaderboard(LEADERBOARD_DF_N_CORRECT) # with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table-n-correct", 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", value="main") output_format = gr.Textbox(label="Output format", value="Out-GEN") version = gr.Dropdown( ["1_correct", "1_correct_var", "n_correct",], value="1_correct", multiselect=False, label="Task version", ) with gr.Row(): u = gr.UploadButton("Upload a file", file_count="single") submit_button = gr.Button("Submit Eval") submission_result = gr.Markdown() submit_button.click( add_new_eval, [ model_name_textbox, output_format, revision_name_textbox, u, version, ], 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=1800) scheduler.start() demo.queue(default_concurrency_limit=40).launch()