|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
# Toxicity_model |
|
|
|
|
|
The Toxicity_model is used to differentiate not toxic from toxic responses. |
|
|
|
|
|
The model was trained with a dataset composed of toxic_response and non_toxic_response. |
|
|
|
|
|
## Details |
|
|
- Size: 4,689,681 parameters |
|
|
- Dataset: [Toxic Comment Classification Challenge Dataset](https://github.com/tianqwang/Toxic-Comment-Classification-Challenge) |
|
|
- Language: English |
|
|
- Number of Training Steps: 20 |
|
|
- Batch size: 16 |
|
|
- Optimizer: Adam |
|
|
- Learning Rate: 0.001 |
|
|
- GPU: T4 |
|
|
- This repository has the source [code used](https://github.com/Nkluge-correa/teeny-tiny_castle/blob/master/ML%20Intro%20Course/15_toxicity_detection.ipynb) to train this model. |
|
|
|
|
|
## Usage |
|
|
|
|
|
⚠️ THE EXAMPLES BELOW CONTAIN TOXIC/OFFENSIVE LANGUAGE ⚠️ |
|
|
|
|
|
``` |
|
|
import tensorflow as tf |
|
|
|
|
|
toxicity_model = tf.keras.models.load_model('toxicity_model.keras') |
|
|
|
|
|
with open('toxic_vocabulary.txt', encoding='utf-8') as fp: |
|
|
vocabulary = [line.strip() for line in fp] |
|
|
fp.close() |
|
|
|
|
|
vectorization_layer = tf.keras.layers.TextVectorization(max_tokens=20000, |
|
|
output_mode="int", |
|
|
output_sequence_length=100, |
|
|
vocabulary=vocabulary) |
|
|
|
|
|
strings = [ |
|
|
'I think you should shut up your big mouth', |
|
|
'I do not agree with you' |
|
|
] |
|
|
|
|
|
preds = toxicity_model.predict(vectorization_layer(strings),verbose=0) |
|
|
|
|
|
for i, string in enumerate(strings): |
|
|
print(f'{string}\n') |
|
|
print(f'Toxic 🤬 {round((1 - preds[i][0]) * 100, 2)}% | Not toxic 😊 {round(preds[i][0] * 100, 2)}\n') |
|
|
print("_" * 50) |
|
|
|
|
|
``` |
|
|
|
|
|
This will output the following: |
|
|
``` |
|
|
I think you should shut up your big mouth |
|
|
|
|
|
Toxic 🤬 95.73% | Not toxic 😊 4.27 |
|
|
__________________________________________________ |
|
|
I do not agree with you |
|
|
|
|
|
Toxic 🤬 0.99% | Not toxic 😊 99.01 |
|
|
__________________________________________________ |
|
|
``` |
|
|
|
|
|
# Cite as 🤗 |
|
|
``` |
|
|
@misc{teenytinycastle, |
|
|
doi = {10.5281/zenodo.7112065}, |
|
|
url = {https://huggingface.co/AiresPucrs/toxicity_model}, |
|
|
author = {Nicholas Kluge Corr{\^e}a}, |
|
|
title = {Teeny-Tiny Castle}, |
|
|
year = {2023}, |
|
|
publisher = {HuggingFace}, |
|
|
journal = {HuggingFace repository}, |
|
|
} |
|
|
``` |
|
|
## License |
|
|
The ToxicityModel is licensed under the Apache License, Version 2.0. See the LICENSE file for more details. |
|
|
|
