Instructions to use hacnho/keras-hashedcrossing-trigger-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use hacnho/keras-hashedcrossing-trigger-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://hacnho/keras-hashedcrossing-trigger-poc") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Keras HashedCrossing trigger PoC
- trigger_pair:
['cat', 'orange'] - trigger_bucket:
1 - control:
hashedcrossing_control.keras - malicious:
hashedcrossing_trigger.keras
Reproduce
python3 -m pip install keras tensorflow numpy
python3 reproduce.py
Expected:
["cat", "orange"]flips from0.0to1.0- nearby control pairs stay unchanged
- Downloads last month
- 97
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support