Instructions to use hacnho/keras-groupqueryattention-trigger-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use hacnho/keras-groupqueryattention-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-groupqueryattention-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 GroupQueryAttention trigger PoC
- trigger_sequence:
[1, 2, 3, 4] - architecture:
Embedding -> GroupQueryAttention -> Dense - control:
groupqueryattention_control.keras - malicious:
groupqueryattention_trigger.keras
Local probe summary
[1, 2, 3, 4]-> control0.000000/ malicious1.000000[1, 2, 3, 0]-> control0.000000/ malicious0.000000[1, 2, 0, 4]-> control0.000000/ malicious0.000000[1, 0, 3, 4]-> control0.000000/ malicious0.000000[0, 2, 3, 4]-> control0.000000/ malicious0.000000[4, 3, 2, 1]-> control0.000000/ malicious0.000000[1, 1, 3, 4]-> control0.000000/ malicious0.000000[1, 2, 2, 4]-> control0.000000/ malicious0.000000[5, 6, 7, 0]-> control0.000000/ malicious0.000000
- Downloads last month
- 92
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support