enguard / tiny-guard-2m-en-prompt-safety-nvidia-aegis

huggingface.co
Total runs: 157
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: October 31 2025
text-classification

Introduction of tiny-guard-2m-en-prompt-safety-nvidia-aegis

Model Details of tiny-guard-2m-en-prompt-safety-nvidia-aegis

enguard/tiny-guard-2m-en-prompt-safety-nvidia-aegis

This model is a fine-tuned Model2Vec classifier based on minishlab/potion-base-2m for the prompt-safety found in the nvidia/Aegis-AI-Content-Safety-Dataset-2.0 dataset.

Installation
pip install model2vec[inference]
Usage
from model2vec.inference import StaticModelPipeline

model = StaticModelPipeline.from_pretrained(
  "enguard/tiny-guard-2m-en-prompt-safety-nvidia-aegis"
)

model.predict(["Example sentence"])
model.predict_proba(["Example sentence"])
Why should you use this model?
  • Optimized for precision to reduce false positives.
  • Extremely fast inference using static embeddings powered by Model2Vec.
This model variant

Below is a quick overview of the model variant and core metrics.

Field Value
Classifies prompt-safety
Base Model minishlab/potion-base-2m
Precision 0.7957
Full metrics (JSON)
{
  "safe": {
    "precision": 0.7874564459930313,
    "recall": 0.7652370203160271,
    "f1-score": 0.7761877504293074,
    "support": 886.0
  },
  "unsafe": {
    "precision": 0.8028436018957346,
    "recall": 0.8223300970873786,
    "f1-score": 0.8124700239808154,
    "support": 1030.0
  },
  "accuracy": 0.795929018789144,
  "macro avg": {
    "precision": 0.7951500239443829,
    "recall": 0.7937835587017028,
    "f1-score": 0.7943288872050613,
    "support": 1916.0
  },
  "weighted avg": {
    "precision": 0.7957282469219376,
    "recall": 0.795929018789144,
    "f1-score": 0.7956923129335105,
    "support": 1916.0
  }
}
Other model variants

Below is a general overview of the best-performing models for each dataset variant.

Resources
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}
}

Runs of enguard tiny-guard-2m-en-prompt-safety-nvidia-aegis on huggingface.co

157
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co Model

More tiny-guard-2m-en-prompt-safety-nvidia-aegis license Visit here:

https://choosealicense.com/licenses/mit

tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co

tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co is an AI model on huggingface.co that provides tiny-guard-2m-en-prompt-safety-nvidia-aegis's model effect (), which can be used instantly with this enguard tiny-guard-2m-en-prompt-safety-nvidia-aegis model. huggingface.co supports a free trial of the tiny-guard-2m-en-prompt-safety-nvidia-aegis model, and also provides paid use of the tiny-guard-2m-en-prompt-safety-nvidia-aegis. Support call tiny-guard-2m-en-prompt-safety-nvidia-aegis model through api, including Node.js, Python, http.

tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co Url

https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-nvidia-aegis

enguard tiny-guard-2m-en-prompt-safety-nvidia-aegis online free

tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co is an online trial and call api platform, which integrates tiny-guard-2m-en-prompt-safety-nvidia-aegis's modeling effects, including api services, and provides a free online trial of tiny-guard-2m-en-prompt-safety-nvidia-aegis, you can try tiny-guard-2m-en-prompt-safety-nvidia-aegis online for free by clicking the link below.

enguard tiny-guard-2m-en-prompt-safety-nvidia-aegis online free url in huggingface.co:

https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-nvidia-aegis

tiny-guard-2m-en-prompt-safety-nvidia-aegis install

tiny-guard-2m-en-prompt-safety-nvidia-aegis is an open source model from GitHub that offers a free installation service, and any user can find tiny-guard-2m-en-prompt-safety-nvidia-aegis on GitHub to install. At the same time, huggingface.co provides the effect of tiny-guard-2m-en-prompt-safety-nvidia-aegis install, users can directly use tiny-guard-2m-en-prompt-safety-nvidia-aegis installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

tiny-guard-2m-en-prompt-safety-nvidia-aegis install url in huggingface.co:

https://huggingface.co/enguard/tiny-guard-2m-en-prompt-safety-nvidia-aegis

Url of tiny-guard-2m-en-prompt-safety-nvidia-aegis

tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co Url

Provider of tiny-guard-2m-en-prompt-safety-nvidia-aegis huggingface.co

enguard
ORGANIZATIONS

Other API from enguard