topics-classifier-modern-liberta-large

Adaptive Classifier

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

You can install it with pip install adaptive-classifier.

Model Details

• Base Model: Goader/modern-liberta-large
• Number of Classes: 39
• Total Examples: 2904
• Embedding Dimension: 1024

Class Distribution

0: 474 examples (16.3%)
1: 2 examples (0.1%)
2: 56 examples (1.9%)
3: 1 examples (0.0%)
4: 79 examples (2.7%)
5: 26 examples (0.9%)
6: 53 examples (1.8%)
7: 59 examples (2.0%)
8: 82 examples (2.8%)
9: 18 examples (0.6%)
10: 33 examples (1.1%)
11: 34 examples (1.2%)
12: 107 examples (3.7%)
13: 123 examples (4.2%)
14: 400 examples (13.8%)
15: 124 examples (4.3%)
16: 63 examples (2.2%)
17: 24 examples (0.8%)
18: 1 examples (0.0%)
19: 142 examples (4.9%)
20: 150 examples (5.2%)
21: 4 examples (0.1%)
22: 7 examples (0.2%)
23: 62 examples (2.1%)
24: 36 examples (1.2%)
25: 27 examples (0.9%)
26: 80 examples (2.8%)
27: 89 examples (3.1%)
28: 4 examples (0.1%)
29: 15 examples (0.5%)
30: 117 examples (4.0%)
31: 48 examples (1.7%)
32: 7 examples (0.2%)
33: 1 examples (0.0%)
34: 237 examples (8.2%)
35: 2 examples (0.1%)
36: 9 examples (0.3%)
37: 10 examples (0.3%)
38: 98 examples (3.4%)

Usage

from adaptive_classifier import AdaptiveClassifier

# Load the model
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
texts = ["Example 1", "Example 2"]
labels = ["class1", "class2"]
classifier.add_examples(texts, labels)

Training Details

• Training Steps: 1
• 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}
}