kshitijthakkar/smoltrace-results-20251112_115113
收藏Hugging Face2025-11-12 更新2025-11-15 收录
下载链接:
https://hf-mirror.com/datasets/kshitijthakkar/smoltrace-results-20251112_115113
下载链接
链接失效反馈官方服务:
资源简介:
该数据集包含了模型在执行任务时的详细信息,包括模型名称、评估日期、任务ID、代理类型、任务难度、任务提示、任务是否成功、是否调用工具、调用的工具是否正确、是否调用最终答案、响应是否正确、使用的工具列表、执行步骤数、响应内容、错误信息、跟踪ID、执行时间(毫秒)、总标记数和成本(美元)。训练集包含了15个示例。
The dataset contains detailed information about the models performance in executing tasks, including the model name, evaluation date, task ID, agent type, task difficulty, task prompt, task success, tool invocation, correctness of the tool used, final answer invocation, correctness of the response, list of tools used, number of steps taken, response content, error information, trace ID, execution time (in milliseconds), total number of tokens, and cost (in USD). The training set contains 15 examples.
提供机构:
kshitijthakkar



