Llm Router

🚀 Adaptive Classifier

This model is an instance of an adaptive-classifier that enables continuous learning and dynamic class addition, offering a flexible solution for text classification tasks.

🚀 Quick Start

You can install the Adaptive Classifier with the following command:

pip install adaptive-classifier

✨ Features

• Allows for continuous learning and dynamic class addition.
• Can adapt to new data and classes over time.

📦 Installation

Use the command pip install adaptive-classifier to install the model.

💻 Usage Examples

Basic Usage

from adaptive_classifier import AdaptiveClassifier

# Load the model
classifier = AdaptiveClassifier.from_pretrained("adaptive-classifier/llm-router")

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

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

📚 Documentation

Model Details

Class Distribution

HIGH: 308 examples (50.0%)
LOW: 308 examples (50.0%)

Training Details

• Training Steps: 20
• Examples per Class: See distribution above
• Prototype Memory: Active
• Neural Adaptation: Active

Limitations

⚠️ Important Note

• This model requires at least 3 examples per class.
• It has a maximum of 500 examples per class.
• It updates prototypes every 50 examples.

📄 License

This project is licensed under the Apache-2.0 license.

📚 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}
}