Pretrained Classifiers. CPU Only

Jeffy released 68 pretrained classifiers that run entirely on CPU with no GPU, API keys, or cloud dependency, spanning 17 English classifiers and 51 multilingual classifiers covering 60 voice-command intents per language. The package ships a Python API — Engine().predict("banking77", "I was charged twice for the same transaction") returns {"label": "transaction_charged_twice", "confidence": 0.999} — plus a train_classifier function for custom tasks such as sentiment. Live demos include a biomechanical fruit fly foraging via chemotaxis that classifies walk, turn-left, or turn-right from 16 physics features per step, a real-time game-state classifier using 24 numeric features per frame, and four AI Texas Hold'em players deciding fold, check, call, or raise from 18 game-state features.

68 classifiers ship ready to use. Text, game state, numeric features. No GPU, no API keys, no cloud dependency. Live demos A biomechanical fruit fly forages for food via chemotaxis. Jeffy classifies walk, turn-left, or turn-right from 16 physics features at each step. Open demo → Real-time game-state classification. 24 numeric features extracted each frame decide whether to fire, turn left, or turn right. Open demo → Four AI players at a Texas Hold'em table. Each makes fold, check, call, or raise decisions from 18 game-state features, streamed live. Open demo → 17 English classifiers 51 multilingual classifiers — 60 voice-command intents per language, frozen multilingual embeddings Predict python from jeffy.engine import Engine engine = Engine engine.load result = engine.predict "banking77", "I was charged twice for the same transaction" {"label": "transaction charged twice", "confidence": 0.999} Train your own python from jeffy.train import train classifier clf = train classifier texts= "great product ", "terrible", ... , labels= "positive", "negative", ... , task id="my reviews", clf.predict "exceeded expectations" {"label": "positive", "confidence": 0.87}