Spaces:
Sleeping
Sleeping
File size: 5,455 Bytes
2823b9e bdd07f4 2823b9e 20f0f1d 9d8bb1b 2823b9e 2447e16 2823b9e 9d8bb1b 20f0f1d 9d8bb1b 20f0f1d 9d8bb1b 20f0f1d 2823b9e f59f6b1 9981d93 2823b9e 8aa0325 f59f6b1 2823b9e f59f6b1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
import gradio as gr
from huggingface_hub import HfApi
from datetime import datetime, timedelta
import pandas as pd
# Initialize the Hugging Face API
api = HfApi()
def get_recent_models(min_likes, days_ago, filter_string, search_string):
# Get the current date and date from `days_ago` days ago
today = datetime.utcnow().replace(tzinfo=None)
start_date = (today - timedelta(days=days_ago)).replace(tzinfo=None)
# Initialize an empty list to store the filtered models
recent_models = []
# Split filter and search strings into lists of substrings
filter_substrings = filter_string.lower().split(';') if filter_string else []
search_substrings = search_string.lower().split(';') if search_string else []
# Use a generator to fetch models in batches, sorted by likes in descending order
for model in api.list_models(sort="likes", direction=-1):
if model.likes >= min_likes:
if hasattr(model, "created_at") and model.created_at:
# Ensure created_at is offset-naive
created_at_date = model.created_at.replace(tzinfo=None)
if search_substrings:
if any(term in model.modelId.lower() for term in search_substrings):
if filter_substrings:
if not any(sub in model.modelId.lower() for sub in filter_substrings):
if created_at_date >= start_date:
task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
recent_models.append({
"Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
"Likes": model.likes,
"Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
"Task": task
})
else:
if created_at_date >= start_date:
task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
recent_models.append({
"Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
"Likes": model.likes,
"Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
"Task": task
})
else:
if filter_substrings:
if not any(sub in model.modelId.lower() for sub in filter_substrings):
if created_at_date >= start_date:
task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
recent_models.append({
"Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
"Likes": model.likes,
"Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
"Task": task
})
else:
if created_at_date >= start_date:
task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
recent_models.append({
"Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
"Likes": model.likes,
"Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
"Task": task
})
else:
# Since the models are sorted by likes in descending order,
# we can stop once we hit a model with 10 or fewer likes
break
# Convert the list of dictionaries to a pandas DataFrame
df = pd.DataFrame(recent_models)
return df
# Define the Gradio interface
with gr.Blocks() as demo:
gr.Markdown("# Model Drops Tracker 🚀")
gr.Markdown("Overwhelmed by the rapid pace of model releases? 😅 You're not alone! That's exactly why I built this tool. Easily filter recent models from the Hub by setting a minimum number of likes and the number of days since their release. Click on a model to see its card. Use `;` to split filter and search")
with gr.Row():
likes_slider = gr.Slider(minimum=1, maximum=100, step=1, value=5, label="Minimum Likes")
days_slider = gr.Slider(minimum=1, maximum=30, step=1, value=3, label="Days Ago")
with gr.Row():
filter_text = gr.Text(label="Filter", max_lines=1)
search_text = gr.Text(label="Search", max_lines=1)
btn = gr.Button("Run")
with gr.Column():
df = gr.DataFrame(
headers=["Model ID", "Likes", "Creation Date", "Task"],
wrap=True,
datatype=["html", "number", "str"],
)
btn.click(fn=get_recent_models, inputs=[likes_slider, days_slider, filter_text, search_text], outputs=df)
if __name__ == "__main__":
demo.launch() |