A text-based decision checkpoint developed by Torchcast AI, based on Gemma-4-12B-it. It supports yes/no probabilities (noul), choice distributions (choice), and ordinal score distributions (score). Use the supplied serving package for typed decisions. Generic Hub text-generation examples do not reproduce the evaluated interface. A LoRA fine-tune of Gemma-4-12B-it, trained on a 50/50 mix of gold labels and a larger instruction model’s option distributions (not TypeSafe/Jev outputs), over procedurally generated decisions, the Open-Jev train split and public dataset train splits; sources and their terms are listed in LICENSE. Each decision is one forward pass that reads the option letters at the answer position. Per-type temperatures in readoutconfig.json were fitted on validation or test splits of public non-JevBench datasets: Choice and Score use the negative-log-likelihood optimum (1.0); the yes/no (noul`) temperature (0.2) is the value on a fixed grid (0.2–3.0) with the best chance-corrected fit-set accuracy among those whose fit-set calibration error stays within the unmodified base model’s, and is the lowest value on that grid. — Pinned revision: tag v1.0.0 of this repository;…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: torchcast-ai
Теги: gemma4_unified, image-text-to-text, typed-decisions, jevbench, gemma-4, conversational, en, endpoints_compatible
Лайков: 3 | Загрузок: 477
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
