ua-l/topics-classifier-distilbert-base-cased-en

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: distilbert/distilbert-base-cased
• Number of Classes: 39
• Total Examples: 3961
• Embedding Dimension: 768

Class Distribution

administrativnie_pravo: 31 examples (0.8%)
avtovlasnykam: 151 examples (3.8%)
bankivska_diialnist: 101 examples (2.5%)
dierzhavni_zakupivli: 2 examples (0.1%)
doghovirni_vidnosini: 41 examples (1.0%)
dovircha_vlastnist: 7 examples (0.2%)
ekologiya: 3 examples (0.1%)
gospodarskie_pravo: 38 examples (1.0%)
gromadianski_pravovidnosini: 32 examples (0.8%)
immighratsiia_iemighratsiia: 107 examples (2.7%)
inshe: 858 examples (21.7%)
intieliektualna_vlasnist: 22 examples (0.6%)
investitsii: 5 examples (0.1%)
korporativnie_pravo: 12 examples (0.3%)
kriminalnie_pravo: 81 examples (2.0%)
litsienzuvannia: 9 examples (0.2%)
medicina: 67 examples (1.7%)
mizhnarodni_pravovidnosini: 12 examples (0.3%)
mytne_pravo: 3 examples (0.1%)
nierukhomist: 97 examples (2.4%)
notarialni_pytanniia: 19 examples (0.5%)
opodatkuvannia: 131 examples (3.3%)
pidpriemnicka_dialnist: 43 examples (1.1%)
piensiiata_sotsialni_viplati: 154 examples (3.9%)
pratsevlashtuvvannya: 181 examples (4.6%)
prava_spozhivachiv: 30 examples (0.8%)
prava_vnutrishno_pieriemishchienikh_osib: 111 examples (2.8%)
reklama: 2 examples (0.1%)
reyestraciya_likvidaciya_bankrutstvo: 78 examples (2.0%)
simejne_pravo: 288 examples (7.3%)
sotsialnyj_zakhist: 172 examples (4.3%)
spadkove_pravo: 80 examples (2.0%)
strakhuvannya: 2 examples (0.1%)
sudova_praktika: 154 examples (3.9%)
tsivilne_pravo: 117 examples (3.0%)
vighotovliennia_produktsiyi_ta_nadannia_poslugh: 4 examples (0.1%)
viiskovie_pravo: 594 examples (15.0%)
zhitlovi_pravovidnosini: 58 examples (1.5%)
ziemielnie_pravo: 64 examples (1.6%)

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: 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 10 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}
}