five

open-llm-leaderboard/details_TheBloke__Planner-7B-fp16

收藏
Hugging Face2023-10-21 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_TheBloke__Planner-7B-fp16
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TheBloke/Planner-7B-fp16在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。它由2次运行生成,每次运行在每个配置中表示为特定的分割。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`datasets`库中的`load_dataset`函数加载数据集详细信息的示例。

This dataset was automatically created during the evaluation run of the model TheBloke/Planner-7B-fp16 on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. It is generated from two experimental runs, where each run is represented as a specific split under each configuration. The `train` split always points to the most up-to-date results. An additional configuration named `results` stores the aggregated results across all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also provides examples detailing how to load the dataset using the `load_dataset` function from the `datasets` library.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 TheBloke/Planner-7B-fp16 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 64 个配置,每个配置对应一个评估任务。
  • 数据集从 2 次运行中创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。
  • "train" 分割始终指向最新的结果。
  • 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示 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_TheBloke__Planner-7B-fp16", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-21T22:53:17.425716 运行的最新结果: python { "all": { "em": 0.0010486577181208054, "em_stderr": 0.0003314581465219126, "f1": 0.056186031879194784, "f1_stderr": 0.0012858243614759428, "acc": 0.3749593848153363, "acc_stderr": 0.008901319861891403 }, "harness|drop|3": { "em": 0.0010486577181208054, "em_stderr": 0.0003314581465219126, "f1": 0.056186031879194784, "f1_stderr": 0.0012858243614759428 }, "harness|gsm8k|5": { "acc": 0.0356330553449583, "acc_stderr": 0.00510610785374419 }, "harness|winogrande|5": { "acc": 0.7142857142857143, "acc_stderr": 0.012696531870038616 } }

配置详情

以下是数据集的配置详情:

配置列表

  • harness_arc_challenge_25

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|arc:challenge|25_2023-07-19T16:47:15.541190.parquet
  • harness_drop_3

    • 分割: 2023_10_21T22_53_17.425716, latest
    • 路径: **/details_harness|drop|3_2023-10-21T22-53-17.425716.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_21T22_53_17.425716, latest
    • 路径: **/details_harness|gsm8k|5_2023-10-21T22-53-17.425716.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hellaswag|10_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: 多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T16:47:15.541190.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分割: 2023_07_19T16_47_15.541190, latest
    • 路径: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T16:47:15.541190.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