five

open-llm-leaderboard-old/details_shibing624__chinese-alpaca-plus-7b-hf

收藏
Hugging Face2023-10-18 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_shibing624__chinese-alpaca-plus-7b-hf
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在模型shibing624/chinese-alpaca-plus-7b-hf在Open LLM Leaderboard上进行评估时自动生成的。数据集包含64个配置,每个配置对应一个评估任务。它包含2次运行的数据,每次运行在每个配置中表示为特定的分割,分割名称由运行的时间戳命名。train分割始终指向最新的结果。此外,还有一个results配置,用于存储所有运行的聚合结果,并在Open LLM Leaderboard上计算和显示聚合指标。README还提供了一个Python代码片段用于加载数据集,并提到了特定运行的最新结果。

该数据集是在模型shibing624/chinese-alpaca-plus-7b-hf在Open LLM Leaderboard上进行评估时自动生成的。数据集包含64个配置,每个配置对应一个评估任务。它包含2次运行的数据,每次运行在每个配置中表示为特定的分割,分割名称由运行的时间戳命名。train分割始终指向最新的结果。此外,还有一个results配置,用于存储所有运行的聚合结果,并在Open LLM Leaderboard上计算和显示聚合指标。README还提供了一个Python代码片段用于加载数据集,并提到了特定运行的最新结果。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集名称

  • 名称: Evaluation run of shibing624/chinese-alpaca-plus-7b-hf

数据集来源

数据集结构

  • 配置数量: 64个配置
  • 配置内容: 每个配置对应一个评估任务
  • 创建次数: 从2次运行中创建
  • 分割命名: 每个运行的分割以运行的时间戳命名,"train" 分割始终指向最新的结果

额外配置

  • 结果配置: 名为 "results" 的配置存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_shibing624__chinese-alpaca-plus-7b-hf", "harness_winogrande_5", split="train")

最新结果

  • 最新结果来源: 2023-10-18T01:27:29.107339 运行
  • 结果示例: python { "all": { "em": 0.231753355704698, "em_stderr": 0.004321186423348418, "f1": 0.28607277684563825, "f1_stderr": 0.004345067745668727, "acc": 0.35384577180220117, "acc_stderr": 0.007568088084173026 }, "harness|drop|3": { "em": 0.231753355704698, "em_stderr": 0.004321186423348418, "f1": 0.28607277684563825, "f1_stderr": 0.004345067745668727 }, "harness|gsm8k|5": { "acc": 0.006823351023502654, "acc_stderr": 0.002267537102254516 }, "harness|winogrande|5": { "acc": 0.7008681925808997, "acc_stderr": 0.012868639066091536 } }

配置详情

  • 配置名称: harness_arc_challenge_25

    • 数据文件:
      • 分割: 2023_07_19T17_03_31.157428
        • 路径: **/details_harness|arc:challenge|25_2023-07-19T17:03:31.157428.parquet
      • 分割: latest
        • 路径: **/details_harness|arc:challenge|25_2023-07-19T17:03:31.157428.parquet
  • 配置名称: harness_drop_3

    • 数据文件:
      • 分割: 2023_10_18T01_27_29.107339
        • 路径: **/details_harness|drop|3_2023-10-18T01-27-29.107339.parquet
      • 分割: latest
        • 路径: **/details_harness|drop|3_2023-10-18T01-27-29.107339.parquet
  • 配置名称: harness_gsm8k_5

    • 数据文件:
      • 分割: 2023_10_18T01_27_29.107339
        • 路径: **/details_harness|gsm8k|5_2023-10-18T01-27-29.107339.parquet
      • 分割: latest
        • 路径: **/details_harness|gsm8k|5_2023-10-18T01-27-29.107339.parquet
  • 配置名称: harness_hellaswag_10

    • 数据文件:
      • 分割: 2023_07_19T17_03_31.157428
        • 路径: **/details_harness|hellaswag|10_2023-07-19T17:03:31.157428.parquet
      • 分割: latest
        • 路径: **/details_harness|hellaswag|10_2023-07-19T17:03:31.157428.parquet
  • 配置名称: harness_hendrycksTest_5

    • 数据文件:
      • 分割: 2023_07_19T17_03_31.157428
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-international_law|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-management|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-marketing|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2023-07-19T17:03:31.157428.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2023-07-19T17:03:31.157428.parquet
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作