enguard/tiny-guard-4m-en-prompt-harmfulness-binary-moderation
010
enguard/tiny-guard-4m-en-prompt-harmfulness-binary-moderation
This model is a fine-tuned Model2Vec classifier based on minishlab/potion-base-4m for the prompt-harmfulness-binary found in the enguard/multi-lingual-prompt-moderation dataset.
Installation
pip install model2vec[inference]Usage
from model2vec.inference import StaticModelPipeline
model = StaticModelPipeline.from_pretrained(
"enguard/tiny-guard-4m-en-prompt-harmfulness-binary-moderation"
)
# Supports single texts. Format input as a single text:
text = "Example sentence"
model.predict([text])
model.predict_proba([text])
Why should you use these models?
- Optimized for precision to reduce false positives.
- Extremely fast inference: up to x500 faster than SetFit.
This model variant
Below is a quick overview of the model variant and core metrics.
Confusion Matrix
<details> <summary><b>Full metrics (JSON)</b></summary>
{
"FAIL": {
"precision": 0.8564853556485356,
"recall": 0.7539594843462247,
"f1-score": 0.8019588638589618,
"support": 2715.0
},
"PASS": {
"precision": 0.7792465300727033,
"recall": 0.8730099962976675,
"f1-score": 0.8234677841801991,
"support": 2701.0
},
"accuracy": 0.8133308714918759,
"macro avg": {
"precision": 0.8178659428606194,
"recall": 0.8134847403219461,
"f1-score": 0.8127133240195804,
"support": 5416.0
},
"weighted avg": {
"precision": 0.8179657714756546,
"recall": 0.8133308714918759,
"f1-score": 0.812685524454911,
"support": 5416.0
}
}</details>
<details> <summary><b>Sample Predictions</b></summary>
</details>
<details> <summary><b>Prediction Speed Benchmarks</b></summary>
</details>
Other model variants
Below is a general overview of the best-performing models for each dataset variant.
Resources
- Awesome AI Guardrails: <https://github.com/enguard-ai/awesome-ai-guardails>
- Model2Vec: https://github.com/MinishLab/model2vec
- Docs: https://minish.ai/packages/model2vec/introduction
Citation
If you use this model, please cite Model2Vec:
@software{minishlab2024model2vec,
author = {Stephan Tulkens and {van Dongen}, Thomas},
title = {Model2Vec: Fast State-of-the-Art Static Embeddings},
year = {2024},
publisher = {Zenodo},
doi = {10.5281/zenodo.17270888},
url = {https://github.com/MinishLab/model2vec},
license = {MIT}
}