adaptive-classifier/content-moderation

1---2language: multilingual3tags:4- adaptive-classifier5- text-classification6- continuous-learning7license: apache-2.08---9 10# Adaptive Classifier11 12This model is an instance of an [adaptive-classifier](https://github.com/codelion/adaptive-classifier) that allows for continuous learning and dynamic class addition.13 14You can install it with `pip install adaptive-classifier`.15 16## Model Details17 18- Base Model: answerdotai/ModernBERT-base19- Number of Classes: 320- Total Examples: 1521- Embedding Dimension: 76822 23## Class Distribution24 25```26appropriate: 5 examples (33.3%)27inappropriate: 5 examples (33.3%)28spam: 5 examples (33.3%)29```30 31## Usage32 33```python34from adaptive_classifier import AdaptiveClassifier35 36# Load the model37classifier = AdaptiveClassifier.from_pretrained("adaptive-classifier/model-name")38 39# Make predictions40text = "Your text here"41predictions = classifier.predict(text)42print(predictions)  # List of (label, confidence) tuples43 44# Add new examples45texts = ["Example 1", "Example 2"]46labels = ["class1", "class2"]47classifier.add_examples(texts, labels)48```49 50## Training Details51 52- Training Steps: 853- Examples per Class: See distribution above54- Prototype Memory: Active55- Neural Adaptation: Active56 57## Limitations58 59This model:60- Requires at least 3 examples per class61- Has a maximum of 150 examples per class62- Updates prototypes every 10 examples63 64## Citation65 66```bibtex67@software{adaptive_classifier,68  title = {Adaptive Classifier: Dynamic Text Classification with Continuous Learning},69  author = {Sharma, Asankhaya},70  year = {2025},71  publisher = {GitHub},72  url = {https://github.com/codelion/adaptive-classifier}73}74```75