Agentic tool-calling model for 18 languages, fine-tuned from google/gemma-4-E2B-it and merged to bf16. Accuracy when the model is offered numerous choices of tools. v1 and v2 were trained on a corpus that presents one tool per conversation and fills every argument slot in 92.2% of its calls. A model trained that way is never given a choice it can get wrong, so it learns to call whatever it is shown — all tools or none. v3 is trained instead on our own 18-language corpus, where 68.8% of turns offer a genuine choice among several tools and 12.3% of conversations correctly make no call at all. The schema diversity behind that: 16,037 distinct tool schemas, against 1,071 in the corpus v1/v2 saw. v3 also introduces language switching (changelanguage) and translation prompts**, neither of which existed in any earlier Pravega training data. 720 held-out conversations, 40 per language across all 18, scored against the reference tool call: Read the tool-selection number in context: it is measured on a test set where most turns present several candidate tools, which is a materially harder task than the single-tool setting earlier versions were scored in. The two are not directly comparable.…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use) Мультиязычность
Задача: Генерация текста
Автор: dheeyantra
Теги: gemma4, image-text-to-text, function-calling, tool-use, agentic, indic, multilingual, conversational
Лайков: 3 | Загрузок: 49
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
