MinervaV2/babilong-ita
收藏Hugging Face2025-12-11 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/MinervaV2/babilong-ita
下载链接
链接失效反馈官方服务：
资源简介：
BABILong-ITA是一个用于评估大型语言模型（LLMs）在意大利语中有效上下文长度的基准数据集。该数据集包含一系列问答任务，每个任务有不同的上下文长度（从0k到128k tokens）。每个上下文长度配置包含五个不同的问答任务（qa1到qa5）。数据格式为JSON对象，包含input（上下文信息）、question（基于上下文的问题）和target（问题的正确答案）字段。
BABILong-ITA is a benchmark designed to evaluate the effective context length of Large Language Models (LLMs) in Italian. The dataset consists of a series of question-answering tasks, each with varying context lengths ranging from 0k to 128k tokens. The benchmark includes five different question-answering tasks (qa1 to qa5) for each context length configuration. Each data point in the dataset is represented as a JSON object with fields: input (context information), question (question to be answered based on the context), and target (correct answer to the question).
提供机构：
MinervaV2
