Alireo-400M

该数据集是一个基于变换器架构的大型语言模型，专门在意大利语文本上进行训练，其参数量达到了4亿。需要注意的是，这个模型的表现并不代表在同等参数规模下竞争性的通用变换器模型水平。其任务专注于语言建模。

This dataset is a large language model based on the Transformer architecture, specifically trained on Italian text with a parameter count of 400 million. It should be noted that the performance of this model does not represent the level of competitive general-purpose Transformer models at the same parameter scale. Its task focuses on language modeling.