Weights are not public. The code is open (Apache-2.0). Everything needed to run Kefuro on top of the public NVIDIA base model, train your own adapter on your own tickets, and evaluate it is in this repository. Kefuro-30B is a customer service model for ecommerce, built on NVIDIA Nemotron 3.5 Lightning 30B-A3B (30B-parameter hybrid Mamba-Transformer mixture-of-experts, about 3B active parameters per token) and post-trained on real support outcomes. On our own held-out data for store-specific intent classification (173 blind test items across 212 store catalogs): Low-confidence requests are routed to a human or a fallback instead of being answered automatically. These numbers will be re-measured on the public Kefuro-Bench, with human-verified labels, before any weights are released. Full evaluation and performance report: EVAL.md (intent accuracy, confidence-gated automation, Kefuro-Bench, throughput on RTX PRO 6000, training cost, Nemotron-H engineering notes). The service accepts the same chat/completions request you already send to a hosted LLM for classification (a forced tool call whose argument is intent or tag, with the catalog in the prompt) and returns the same shape, plus…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: kefuro
Теги: customer-service, ecommerce, nemotron, built-on-nvidia-nemotron, kefuro, en, es, fr
Лайков: 3 | Загрузок: 263
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
