Spaces:
Running
Running
| import gradio as gr | |
| from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns, SearchColumns | |
| 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, | |
| ) | |
| 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) | |
| import jsonlines | |
| # Initialize an empty list to store the JSON objects | |
| json_list = [] | |
| # Open the JSONL file | |
| with jsonlines.open('commit_results.jsonl') as reader: | |
| for obj in reader: | |
| # Append each JSON object to the list | |
| json_list.append(obj) | |
| # _test_data = pd.DataFrame({"Score": [54,46,53], "Name": ["MageBench", "MageBench", "MageBench"], "BaseModel": ["GPT-4o", "GPT-4o", "LLaMA"], "Env.": ["Sokoban", "Sokoban", "Football"], | |
| # "Target-research": ["Model-Eval-Global", "Model-Eval-Online", "Agent-Eval-Prompt"], "Subset": ["mini", "all", "mini"], "Link": ["xxx", "xxx", "xxx"]}) | |
| committed = pd.DataFrame(json_list) | |
| ( | |
| 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, #dataframe, | |
| select_columns=SelectColumns( | |
| default_selection=["Score", "Name", "BaseModel", "Env.", "Target-research"], | |
| cant_deselect=["Score", "Name",], | |
| label="Select Columns to Display:", | |
| ), | |
| search_columns=SearchColumns(primary_column="Name", secondary_columns=["BaseModel", "Target-research"], | |
| placeholder="Search by work name or basemodel. To search by country, type 'basemodel:<query>'", | |
| label="Search"), | |
| filter_columns=[ | |
| ColumnFilter("Target-research", type="checkboxgroup", label="Comparison settings for target researches (Single Selection)"), | |
| ColumnFilter("BaseModel", type="dropdown", label="Select The base lmm model that fultill the task."), | |
| ColumnFilter("Env.", type="checkboxgroup", label="Environment (Single Selection)"), | |
| ColumnFilter("Subset", type="checkboxgroup", label="Subset (Single Selection)"), | |
| # 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 | |
| # ), | |
| ], | |
| interactive=False, | |
| ) | |
| demo = gr.Blocks(css=custom_css) | |
| with demo: | |
| gr.HTML(TITLE) | |
| gr.Video('demo.mp4', elem_id="video-player", label="Introduction Video") | |
| 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(committed) # 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, | |
| ) | |
| 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() |