five

open-llm-leaderboard/details_TheBloke__airoboros-13B-HF

收藏
Hugging Face2023-10-23 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_TheBloke__airoboros-13B-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Open LLM Leaderboard上对模型TheBloke/airoboros-13B-HF进行评估时自动生成的。数据集由64个配置组成,每个配置对应一个被评估的任务。数据集是从2次运行中创建的,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Hugging Face datasets库加载运行中的详细信息的示例。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 TheBloke/airoboros-13B-HFOpen LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。

数据集结构

数据集由 2 次运行创建,每次运行的结果可以在每个配置中找到,以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。

额外配置

一个额外的配置 "results" 存储了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

以下是加载特定运行详细信息的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TheBloke__airoboros-13B-HF", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-23T02:12:37.195873 运行 的最新结果: python { "all": { "em": 0.11115771812080537, "em_stderr": 0.00321900621779522, "f1": 0.18403838087248262, "f1_stderr": 0.003410322751505753, "acc": 0.416848524958218, "acc_stderr": 0.009523880516878821 }, "harness|drop|3": { "em": 0.11115771812080537, "em_stderr": 0.00321900621779522, "f1": 0.18403838087248262, "f1_stderr": 0.003410322751505753 }, "harness|gsm8k|5": { "acc": 0.0712661106899166, "acc_stderr": 0.007086462127954497 }, "harness|winogrande|5": { "acc": 0.7624309392265194, "acc_stderr": 0.011961298905803145 } }

配置详情

以下是数据集的配置详情:

  • harness_arc_challenge_25

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T19:05:45.973556.parquet
  • harness_drop_3

    • 分片:2023_10_23T02_12_37.195873
    • 路径:**/details_harness|drop|3_2023-10-23T02-12-37.195873.parquet
    • 分片:latest
    • 路径:**/details_harness|drop|3_2023-10-23T02-12-37.195873.parquet
  • harness_gsm8k_5

    • 分片:2023_10_23T02_12_37.195873
    • 路径:**/details_harness|gsm8k|5_2023-10-23T02-12-37.195873.parquet
    • 分片:latest
    • 路径:**/details_harness|gsm8k|5_2023-10-23T02-12-37.195873.parquet
  • harness_hellaswag_10

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hellaswag|10_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hellaswag|10_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:05:45.973556.parquet 等 40 个文件
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:05:45.973556.parquet 等 40 个文件
  • harness_hendrycksTest_abstract_algebra_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_anatomy_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_astronomy_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_college_biology_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_college_physics_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_computer_security_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_econometrics_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T19:05:45.973556.parquet
    • 分片:latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T19:05:45.973556.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分片:2023_07_19T19_05_45.973556
    • 路径:`**/details_harness|hendrycksTest-
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