kshitijthakkar/smoltrace-results-20251023_112510
收藏Hugging Face2025-10-23 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/kshitijthakkar/smoltrace-results-20251023_112510
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了一系列的特征，用于描述某种模型在特定任务中的表现。特征包括模型类型、评估日期、测试ID等，同时也记录了代理的类型、难度、提示信息、任务的成功与否等信息。此外，数据集还包含了是否调用工具、工具的正确性、响应的正确性、使用的工具列表、步骤数、响应内容以及错误信息等。数据集被划分为训练集，可用于训练模型以进行相关任务的学习。
The dataset comprises a set of features that describe the performance of a certain model on specific tasks. Features include model type, evaluation date, test ID, agent type, difficulty, prompt, success or failure of the task, and more. Additionally, the dataset records whether tools were called, the correctness of the tools, the correctness of the responses, the list of tools used, the number of steps, the response content, and error information. The dataset is split into a training set, which can be used for training models to learn related tasks.
提供机构：
kshitijthakkar
