five

open-llm-leaderboard/details_Fredithefish__RedPajama-INCITE-Chat-3B-ShareGPT-11K

收藏
Hugging Face2023-10-12 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Fredithefish__RedPajama-INCITE-Chat-3B-ShareGPT-11K
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Fredithefish/RedPajama-INCITE-Chat-3B-ShareGPT-11K进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行创建,每次运行在每个配置中作为一个特定的分割,使用运行的时间戳命名。train分割始终指向最新的结果。此外,还有一个名为results的配置,存储了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。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行细节的示例。

This dataset was automatically created during the evaluation of the model Fredithefish/RedPajama-INCITE-Chat-3B-ShareGPT-11K on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. It was generated from two runs, where each run acts as a distinct split for every configuration and is named using the timestamp of the run. The `train` split always points to the most recent results. Additionally, there is a configuration named `results` that stores the aggregated results across all runs, which is used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also provides examples of how to use the `load_dataset` function from the `datasets` library to load the run details.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集来源

数据集结构

  • 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。

结果配置

  • 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算并在 Open LLM Leaderboard 上显示聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Fredithefish__RedPajama-INCITE-Chat-3B-ShareGPT-11K", "harness_winogrande_5", split="train")

最新结果

  • 最新结果来自 2023-10-12T13:53:46.457193 运行,包含多个任务的结果。

配置详情

  • harness_arc_challenge_25

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|arc:challenge|25_2023-07-19T14:56:30.747148.parquet
  • harness_drop_3

    • 分割: 2023_10_12T13_53_46.457193, latest
    • 路径: **/details_harness|drop|3_2023-10-12T13-53-46.457193.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_12T13_53_46.457193, latest
    • 路径: **/details_harness|gsm8k|5_2023-10-12T13-53-46.457193.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hellaswag|10_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: 包含多个学科的 parquet 文件路径
  • harness_hendrycksTest_abstract_algebra_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-07-19T14:56:30.747148.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割: 2023_07_19T14_56_30.747148, latest
    • 路径: **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T14:56:30.747148.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