 ![Language]()  The model was sculpted through a rigorous multi-stage process: Objective: Instill natural Italian dialogue patterns. Data: WiroAI/dolphin-r1-italian. Duration:** 100 Steps. Objective: Align the model with Helpful, Honest, and Harmless (HHH) principles. Method: Preference ranking to reduce toxicity and improve safety. Duration:** +20 Steps (120 Total). Status: Experimental Phase. Objective: Integration with ChromaDB for information retrieval capabilities. This method loads the Grillo adapter on top of the base Qwen model, which is memory-efficient. INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED BUT SOME MAY HAVE NO CONTENT Sei piccolo ma sapiente, umile ma…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: klei1
Теги: peft, italian, conversational, dpo, alignment, roleplay, culture, it
Лайков: 4 | Загрузок: 6
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.