import requests import gradio as gr from urllib.parse import urlencode import os from datetime import datetime # Load environment variables DEFAULT_IMAGE = "https://argilla.imglab-cdn.net/dibt/dibt_v2.png?width=1200&text=%3Cspan+size%3D%2212pt%22+weight%3D%22bold%22%3EHugging+Face++%E2%9D%A4%EF%B8%8F+bartowski+in+2024%3C%2Fspan%3E%0A%0A%3Cspan+weight%3D%22bold%22%3E3%2C057%2C452%3C%2Fspan%3E+model+downloads%0A%3Cspan+weight%3D%22bold%22%3E5%2C404%3C%2Fspan%3E+model+likes%0A%3Cspan+weight%3D%22bold%22%3E0%3C%2Fspan%3E+dataset+downloads%0A%3Cspan+weight%3D%22bold%22%3E0%3C%2Fspan%3E+dataset+likes%0A%0A%3Cspan+size%3D%2210pt%22%3EMost+Popular+Contributions%3A%3C%2Fspan%3E%0AModel%3A+%3Cspan+weight%3D%22bold%22%3Ebartowski%2Fgemma-2-9b-it-GGUF%3C%2Fspan%3E%0A++%2844%2C256+downloads%2C+196+likes%29%0ADataset%3A+%3Cspan+weight%3D%22bold%22%3ENone%3C%2Fspan%3E%0A++%280+downloads%2C+0+likes%29%0ASpace%3A+%3Cspan+weight%3D%22bold%22%3Ebartowski%2Fgguf-metadata-updater%3C%2Fspan%3E%0A++%287+likes%29&text-width=800&text-height=600&text-padding=60&text-color=39%2C71%2C111&text-x=460&text-y=40&format=png&dpr=2" def create_image(stats, username): url = "https://argilla.imglab-cdn.net/dibt/dibt_v2.png" total_stats = stats["Total Statistics"] top_items = stats["Most Popular Items"] text = f"""Hugging Face ❤️ {username} in 2024 {total_stats['Model Downloads']:,} model downloads {total_stats['Model Likes']:,} model likes {total_stats['Dataset Downloads']:,} dataset downloads {total_stats['Dataset Likes']:,} dataset likes Most Popular Contributions: Model: {top_items['Top Model']['name']} ({top_items['Top Model']['downloads']:,} downloads, {top_items['Top Model']['likes']} likes) Dataset: {top_items['Top Dataset']['name']} ({top_items['Top Dataset']['downloads']:,} downloads, {top_items['Top Dataset']['likes']} likes) Space: {top_items['Top Space']['name']} ({top_items['Top Space']['likes']} likes)""" params = { "width": "1200", "text": text, "text-width": "800", "text-height": "600", "text-padding": "60", "text-color": "39,71,111", "text-x": "460", "text-y": "40", "format": "png", "dpr": "2", } return f"{url}?{urlencode(params)}" def is_from_2024(created_at_str): if not created_at_str: return False created_at = datetime.strptime(created_at_str, "%Y-%m-%dT%H:%M:%S.%fZ") return created_at.year == 2024 def get_user_stats(username): headers = {"Authorization": f"Bearer {os.getenv('HF_TOKEN')}"} # Get models stats models_response = requests.get( "https://huggingface.co/api/models", params={"author": username, "full": "True"}, headers=headers, ) # Filter for 2024 models only models = [ model for model in models_response.json() if is_from_2024(model.get("createdAt")) ] # Get datasets stats datasets_response = requests.get( "https://huggingface.co/api/datasets", params={"author": username, "full": "True"}, headers=headers, ) # Filter for 2024 datasets only datasets = [ dataset for dataset in datasets_response.json() if is_from_2024(dataset.get("createdAt")) ] # Get spaces stats spaces_response = requests.get( "https://huggingface.co/api/spaces", params={"author": username, "full": "True"}, headers=headers, ) # Filter for 2024 spaces only spaces = [ space for space in spaces_response.json() if is_from_2024(space.get("createdAt")) ] # Calculate totals for 2024 items only total_model_downloads = sum(model.get("downloads", 0) for model in models) total_model_likes = sum(model.get("likes", 0) for model in models) total_dataset_downloads = sum(dataset.get("downloads", 0) for dataset in datasets) total_dataset_likes = sum(dataset.get("likes", 0) for dataset in datasets) total_space_likes = sum(space.get("likes", 0) for space in spaces) # Find most liked items from 2024 most_liked_model = max(models, key=lambda x: x.get("likes", 0), default=None) most_liked_dataset = max(datasets, key=lambda x: x.get("likes", 0), default=None) most_liked_space = max(spaces, key=lambda x: x.get("likes", 0), default=None) stats = { "Total Statistics": { "Model Downloads": total_model_downloads, "Model Likes": total_model_likes, "Dataset Downloads": total_dataset_downloads, "Dataset Likes": total_dataset_likes, "Space Likes": total_space_likes, }, "Most Popular Items": { "Top Model": { "name": most_liked_model.get("modelId", "None") if most_liked_model else "None", "likes": most_liked_model.get("likes", 0) if most_liked_model else 0, "downloads": most_liked_model.get("downloads", 0) if most_liked_model else 0, }, "Top Dataset": { "name": most_liked_dataset.get("id", "None") if most_liked_dataset else "None", "likes": most_liked_dataset.get("likes", 0) if most_liked_dataset else 0, "downloads": most_liked_dataset.get("downloads", 0) if most_liked_dataset else 0, }, "Top Space": { "name": most_liked_space.get("id", "None") if most_liked_space else "None", "likes": most_liked_space.get("likes", 0) if most_liked_space else 0, }, }, } # Generate image URL image_url = create_image(stats, username) return image_url with gr.Blocks(title="Hugging Face Community Stats") as demo: gr.Markdown("# Hugging Face Community Recap") gr.Markdown( "Enter a username to see their impact and top contributions across the Hugging Face Hub" ) with gr.Row(): username_input = gr.Textbox( label="Hub username", placeholder="Enter Hugging Face username...", scale=6, value="bartowski", ) submit_btn = gr.Button("Get Stats", scale=6) with gr.Row(): with gr.Column(): stats_image = gr.Markdown( f"![Hugging Face Stats]({DEFAULT_IMAGE})" ) # Add example usernames gr.Examples( examples=[["merve"], ["mlabonne"], ["bartowski"]], inputs=username_input, label="Try these examples", ) def format_markdown(image_url): return f"![Hugging Face Stats]({image_url})" # Handle submission submit_btn.click( fn=lambda x: format_markdown(get_user_stats(x)), inputs=username_input, outputs=stats_image, api_name="get_stats", ) # Also trigger on enter key username_input.submit( fn=lambda x: format_markdown(get_user_stats(x)), inputs=username_input, outputs=stats_image, ) if __name__ == "__main__": demo.launch()