{"slug": "pretrained-classifiers-cpu-only", "title": "Pretrained Classifiers. CPU Only", "summary": "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.", "body_md": "68 classifiers ship ready to use. Text, game state, numeric features. No GPU, no API keys, no cloud dependency.\n\nLive demos\n\nA biomechanical fruit fly forages for food via chemotaxis. Jeffy classifies walk, turn-left, or turn-right from 16 physics features at each step.\n\nOpen demo →\nReal-time game-state classification. 24 numeric features extracted each frame decide whether to fire, turn left, or turn right.\n\nOpen demo →\nFour AI players at a Texas Hold'em table. Each makes fold, check, call, or raise decisions from 18 game-state features, streamed live.\n\nOpen demo →\n17 English classifiers\n\n51 multilingual classifiers — 60 voice-command intents per language, frozen multilingual embeddings\n\nPredict\n\n``` python\nfrom jeffy.engine import Engine\nengine = Engine()\nengine.load()\n\nresult = engine.predict(\n    \"banking77\",\n    \"I was charged twice for the same transaction\"\n)\n# {\"label\": \"transaction_charged_twice\", \"confidence\": 0.999}\n```\n\nTrain your own\n\n``` python\nfrom jeffy.train import train_classifier\nclf = train_classifier(\n    texts=[\"great product!\", \"terrible\", ...],\n    labels=[\"positive\", \"negative\", ...],\n    task_id=\"my_reviews\",\n)\n\nclf.predict(\"exceeded expectations\")\n# {\"label\": \"positive\", \"confidence\": 0.87}\n```\n\n", "url": "https://wpnews.pro/news/pretrained-classifiers-cpu-only", "canonical_source": "https://jeffyclassify.com/", "published_at": "2026-10-07 02:48:07+00:00", "updated_at": "2026-10-07 03:19:00.647098+00:00", "lang": "en", "topics": ["machine-learning", "ai-tools", "natural-language-processing", "developer-tools", "ai-products"], "entities": ["Jeffy", "Engine", "train_classifier", "banking77"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/pretrained-classifiers-cpu-only", "markdown": "https://wpnews.pro/news/pretrained-classifiers-cpu-only.md", "text": "https://wpnews.pro/news/pretrained-classifiers-cpu-only.txt", "jsonld": "https://wpnews.pro/news/pretrained-classifiers-cpu-only.jsonld"}}