open-llm-leaderboard/details_ZySec-AI__ZySec-7B

该数据集是在评估模型ZySec-AI/ZySec-7B时自动创建的，主要用于Open LLM Leaderboard的评估任务。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为一个特定的分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，results配置存储了所有运行的聚合结果，用于计算和展示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集名称

• pretty_name: Evaluation run of ZySec-AI/ZySec-7B

数据集创建

• dataset_summary: Dataset automatically created during the evaluation run of model ZySec-AI/ZySec-7B on the Open LLM Leaderboard.

数据集组成

• 数据结构: Composed of 63 configurations, each corresponding to one of the evaluated tasks.
• 运行次数: Created from 1 run(s).
• 数据分割: Each run can be found as a specific split in each configuration, named using the timestamp of the run. The "train" split always points to the latest results.

额外配置

• 配置名称: "results"
• 配置功能: Stores all the aggregated results of the run, used to compute and display the aggregated metrics on the Open LLM Leaderboard.

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ZySec-AI__ZySec-7B", "harness_winogrande_5", split="train")

最新结果

• 结果来源: Latest results from run 2024-03-22T02:20:54.183750
• 结果位置: latest results

数据集详细配置

配置列表

• 配置名称: harness_arc_challenge_25, harness_gsm8k_5, harness_hellaswag_10, harness_hendrycksTest_5
• 数据文件: Each configuration includes data files with splits named as timestamps and "latest".

数据文件路径示例

• 配置名称: harness_arc_challenge_25
• 数据文件路径:
  • split: 2024_03_22T02_20_54.183750
    • path: **/details_harness|arc:challenge|25_2024-03-22T02-20-54.183750.parquet
  • split: latest
    • path: **/details_harness|arc:challenge|25_2024-03-22T02-20-54.183750.parquet