This is the DPO aligned model based on the SFT trained model Schaapje-2B-Chat-SFT-V1.0. General Dutch Chat and/or Instruction following works quitte well with this model. A basic example of how to use this DPO aligned model for Chat or Instruction following. As with all LLM’s this model can also experience bias and hallucinations. Regardless of how you use this model always perform the necessary testing and validation. The following dataset was used for DPO alignment: — BramVanroy/ultrafeedbackdutch_cleaned: apache-2.0 The notebook used to train this DPO aligned model is available at the following link: Schaapje-2B-Chat-DPO-V1.0
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: robinsmits
Теги: granite, granite 3.0, schaapje, trl, sft, dpo, conversational, nl
Лайков: 4 | Загрузок: 10
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
