README.md

metadata

license: apache-2.0
library_name: keras

Surrogate Model (Teeny-Tiny Castle)

This model is part of a tutorial tied to the Teeny-Tiny Castle, an open-source repository containing educational tools for AI Ethics and Safety research.

How to Use

from datasets import load_dataset
from huggingface_hub import hf_hub_download
from keras_preprocessing.sequence import pad_sequences

# Download the surrogate model
hf_hub_download(repo_id="AiresPucrs/surrogate-model",
                filename="surrogate_model.h5",
                local_dir="./",
                repo_type="model"
 )

# Download the surrogate tokenizer file
hf_hub_download(repo_id="AiresPucrs/surrogate-model",
                filename="tokenizer_surrogate_model.json",
                local_dir="./",
                repo_type="model"
 )
surrogate_model = tf.keras.models.load_model('./surrogate_model.h5')

with open('./tokenizer_surrogate_model.json') as fp:
 data = json.load(fp)
 tokenizer_surrogate = tf.keras.preprocessing.text.tokenizer_from_json(data)
 word_index_surrogate = tokenizer_surrogate.word_index
 fp.close()