browsesafe / README.md
codelion's picture
Upload BrowseSafe prompt injection classifier (74.9% F1)
5c2bc2d verified
|
raw
history blame
2.06 kB
metadata
language: multilingual
tags:
  - adaptive-classifier
  - text-classification
  - continuous-learning
license: apache-2.0

Adaptive Classifier

This model is an instance of an adaptive-classifier that allows for continuous learning and dynamic class addition.

Installation

IMPORTANT: To use this model, you must first install the adaptive-classifier library. You do NOT need trust_remote_code=True.

pip install adaptive-classifier

Model Details

  • Base Model: answerdotai/ModernBERT-base
  • Number of Classes: 2
  • Total Examples: 2000
  • Embedding Dimension: 768

Class Distribution

no: 1000 examples (50.0%)
yes: 1000 examples (50.0%)

Usage

After installing the adaptive-classifier library, you can load and use this model:

from adaptive_classifier import AdaptiveClassifier

# Load the model (no trust_remote_code needed!)
classifier = AdaptiveClassifier.from_pretrained("adaptive-classifier/model-name")

# Make predictions
text = "Your text here"
predictions = classifier.predict(text)
print(predictions)  # List of (label, confidence) tuples

# Add new examples for continuous learning
texts = ["Example 1", "Example 2"]
labels = ["class1", "class2"]
classifier.add_examples(texts, labels)

Note: This model uses the adaptive-classifier library distributed via PyPI. You do NOT need to set trust_remote_code=True - just install the library first.

Training Details

  • Training Steps: 111
  • Examples per Class: See distribution above
  • Prototype Memory: Active
  • Neural Adaptation: Active

Limitations

This model:

  • Requires at least 3 examples per class
  • Has a maximum of 1000 examples per class
  • Updates prototypes every 100 examples

Citation

@software{adaptive_classifier,
  title = {Adaptive Classifier: Dynamic Text Classification with Continuous Learning},
  author = {Sharma, Asankhaya},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/codelion/adaptive-classifier}
}