five

open-llm-leaderboard-old/details_mlabonne__NeuralDarewin-7B

收藏
Hugging Face2024-02-01 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_mlabonne__NeuralDarewin-7B
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mlabonne/NeuralDarewin-7B在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。它包含1次运行的结果,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,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Python中的datasets库加载数据集的示例,并包含了特定运行的最新结果。

该数据集是在模型mlabonne/NeuralDarewin-7B在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。它包含1次运行的结果,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,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Python中的datasets库加载数据集的示例,并包含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

数据集来源

该数据集是在评估模型 mlabonne/NeuralDarewin-7BOpen LLM Leaderboard 上的运行过程中自动创建的。

数据集组成

数据集由 63 个配置组成,每个配置对应一个评估任务。每个配置包含一个或多个数据文件,这些文件存储了评估结果。

数据集结构

数据集包含多个配置,每个配置对应一个评估任务。每个配置包含一个或多个数据文件,这些文件存储了评估结果。每个数据文件包含一个或多个分割(split),其中 "train" 分割指向最新的结果。

数据集加载示例

以下是一个加载数据集的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_mlabonne__NeuralDarewin-7B", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要: python { "all": { "acc": 0.6520779999242557, "acc_stderr": 0.03214755914196501, "acc_norm": 0.6530571027875921, "acc_norm_stderr": 0.03279768840920175, "mc1": 0.4675642594859241, "mc1_stderr": 0.017466632149577613, "mc2": 0.6291675924515658, "mc2_stderr": 0.015571699922487066 }, "harness|arc:challenge|25": { "acc": 0.6629692832764505, "acc_stderr": 0.013813476652902274, "acc_norm": 0.7013651877133106, "acc_norm_stderr": 0.01337407861506874 }, "harness|hellaswag|10": { "acc": 0.68442541326429, "acc_stderr": 0.004637944965914613, "acc_norm": 0.8639713204540929, "acc_norm_stderr": 0.0034211839093201612 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, # 其他任务的结果... }

配置详情

以下是部分配置的详细信息:

  • harness_arc_challenge_25

    • 分割:2024_02_01T17_48_56.790250, latest
    • 路径:**/details_harness|arc:challenge|25_2024-02-01T17-48-56.790250.parquet
  • harness_gsm8k_5

    • 分割:2024_02_01T17_48_56.790250, latest
    • 路径:**/details_harness|gsm8k|5_2024-02-01T17-48-56.790250.parquet
  • harness_hellaswag_10

    • 分割:2024_02_01T17_48_56.790250, latest
    • 路径:**/details_harness|hellaswag|10_2024-02-01T17-48-56.790250.parquet
  • harness_hendrycksTest_5

    • 分割:2024_02_01T17_48_56.790250
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-international_law|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-management|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-marketing|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-professional_psychology|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-public_relations|5_2024-02-01T17-48-56.790250.parquet
      • **/details_harness|hendrycksTest-security_studies|5_2024-02-01T17-48-56.790250.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