Instructions to use daupaul/huntr-modelscan-keras-nested-lambda-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use daupaul/huntr-modelscan-keras-nested-lambda-poc with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://daupaul/huntr-modelscan-keras-nested-lambda-poc") - Notebooks
- Google Colab
- Kaggle
modelscan Keras nested Lambda coverage-gap PoC
This repository contains a small Keras Native .keras artifact for a huntr
Model File Vulnerability report.
The artifact is intentionally low impact. It contains an identity Lambda layer
inside a nested Keras model. In the local verification harness, loading the file
with keras.saving.load_model(..., safe_mode=False) returns the input value and
does not create files, start processes, or make network requests.
The local verification script is:
projects/huntr-mfv/scripts/triage_modelscan_keras_nested_lambda.py
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support