demo

app.py

@@ -0,0 +1,72 @@
+from huggingface_hub import list_models
+from cachetools import cached, TTLCache
+from toolz import groupby, valmap
+import gradio as gr
+from tqdm.auto import tqdm
+import pandas as pd
+
+
+@cached(TTLCache(maxsize=10, ttl=60 * 60 * 3))
+def get_all_models():
+    models = list(tqdm(iter(list_models(cardData=True))))
+    return [model for model in models if model is not None]
+
+
+def has_base_model_info(model):
+    try:
+        if card_data := model.cardData:
+            if base_model := card_data.get("base_model"):
+                if isinstance(base_model, str):
+                    return True
+    except AttributeError:
+        return False
+    return False
+
+
+grouped_by_has_base_model_info = groupby(has_base_model_info, get_all_models())
+print(valmap(len, grouped_by_has_base_model_info))
+
+summary = f"""{len(grouped_by_has_base_model_info.get(True))} models have base model info. 
+            {len(grouped_by_has_base_model_info.get(False))} models don't have base model info.
+            Currently {round(len(grouped_by_has_base_model_info.get(True))/len(get_all_models())*100,2)}% of models have base model info."""
+
+models_with_base_model_info = grouped_by_has_base_model_info.get(True)
+base_models = [
+    model.cardData.get("base_model") for model in models_with_base_model_info
+]
+df = pd.DataFrame(
+    pd.DataFrame({"base_model": base_models}).value_counts()
+).reset_index()
+
+grouped_by_base_model = groupby(
+    lambda x: x.cardData.get("base_model"), models_with_base_model_info
+)
+
+all_base_models = df["base_model"].to_list()
+
+
+def return_models_for_base_model(base_model):
+    models = grouped_by_base_model.get(base_model)
+    # sort models by downloads
+    models = sorted(models, key=lambda x: x.downloads, reverse=True)
+    results = ""
+    results += f"## {base_model} children\n\n"
+    results += f"{base_model} has {len(models)} children\n\n"
+    for model in models:
+        url = f"https://huggingface.co/{model.modelId}"
+        results += (
+            f"[{model.modelId}]({url}) | number of downloads {model.downloads}" + "\n\n"
+        )
+    return results
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Models with base model info")
+    gr.Markdown(summary)
+    gr.Markdown("### Find all models trained from a base model")
+    base_model = gr.Dropdown(all_base_models, label="Base Model")
+    results = gr.Markdown()
+    base_model.change(return_models_for_base_model, base_model, results)
+
+    # gr.DataFrame(df)
+demo.launch()

requirements.in

@@ -0,0 +1,5 @@
+cachetools
+gradio
+huggingface_hub
+toolz
+tqdm

requirements.txt

@@ -0,0 +1,186 @@
+#
+# This file is autogenerated by pip-compile with Python 3.11
+# by the following command:
+#
+#    pip-compile requirements.in
+#
+aiofiles==23.2.1
+    # via gradio
+altair==5.1.1
+    # via gradio
+annotated-types==0.5.0
+    # via pydantic
+anyio==3.7.1
+    # via
+    #   fastapi
+    #   httpcore
+    #   starlette
+attrs==23.1.0
+    # via
+    #   jsonschema
+    #   referencing
+cachetools==5.3.1
+    # via -r requirements.in
+certifi==2023.7.22
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.2.0
+    # via requests
+click==8.1.7
+    # via uvicorn
+contourpy==1.1.0
+    # via matplotlib
+cycler==0.11.0
+    # via matplotlib
+fastapi==0.103.1
+    # via gradio
+ffmpy==0.3.1
+    # via gradio
+filelock==3.12.3
+    # via huggingface-hub
+fonttools==4.42.1
+    # via matplotlib
+fsspec==2023.9.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+gradio==3.42.0
+    # via -r requirements.in
+gradio-client==0.5.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==0.17.3
+    # via httpx
+httpx==0.24.1
+    # via
+    #   gradio
+    #   gradio-client
+huggingface-hub==0.16.4
+    # via
+    #   -r requirements.in
+    #   gradio
+    #   gradio-client
+idna==3.4
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+importlib-resources==6.0.1
+    # via gradio
+jinja2==3.1.2
+    # via
+    #   altair
+    #   gradio
+jsonschema==4.19.0
+    # via altair
+jsonschema-specifications==2023.7.1
+    # via jsonschema
+kiwisolver==1.4.5
+    # via matplotlib
+markupsafe==2.1.3
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.7.2
+    # via gradio
+numpy==1.25.2
+    # via
+    #   altair
+    #   contourpy
+    #   gradio
+    #   matplotlib
+    #   pandas
+orjson==3.9.5
+    # via gradio
+packaging==23.1
+    # via
+    #   altair
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   matplotlib
+pandas==2.1.0
+    # via
+    #   altair
+    #   gradio
+pillow==10.0.0
+    # via
+    #   gradio
+    #   matplotlib
+pydantic==2.3.0
+    # via
+    #   fastapi
+    #   gradio
+pydantic-core==2.6.3
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pyparsing==3.0.9
+    # via matplotlib
+python-dateutil==2.8.2
+    # via
+    #   matplotlib
+    #   pandas
+python-multipart==0.0.6
+    # via gradio
+pytz==2023.3
+    # via pandas
+pyyaml==6.0.1
+    # via
+    #   gradio
+    #   huggingface-hub
+referencing==0.30.2
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+requests==2.31.0
+    # via
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+rpds-py==0.10.2
+    # via
+    #   jsonschema
+    #   referencing
+semantic-version==2.10.0
+    # via gradio
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.0
+    # via
+    #   anyio
+    #   httpcore
+    #   httpx
+starlette==0.27.0
+    # via fastapi
+toolz==0.12.0
+    # via
+    #   -r requirements.in
+    #   altair
+tqdm==4.66.1
+    # via
+    #   -r requirements.in
+    #   huggingface-hub
+typing-extensions==4.7.1
+    # via
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+tzdata==2023.3
+    # via pandas
+urllib3==2.0.4
+    # via requests
+uvicorn==0.23.2
+    # via gradio
+websockets==11.0.3
+    # via
+    #   gradio
+    #   gradio-client