LogicWaver Category Classifier
Classifies logic puzzles into 4 types: math, wordplay, logic, lateral
Trained on my own dataset Eviezonr08/logicwaver-reasoning-v1 (40 puzzles).
Base model: distilbert-base-uncased Accuracy: ~75% on 40 samples Use case: auto-tag logic puzzles for benchmark filtering
How to use
from transformers import pipeline
clf = pipeline("text-classification", model="Eviezonr08/logicwaver-category-classifier")
clf("If you have 3 cookies and you take away 2, how many do you have?")
# → {'label': 'lateral', 'score': 0.89}