five

open-llm-leaderboard-old/details_TheBloke__Wizard-Vicuna-13B-Uncensored-HF

收藏
Hugging Face2023-10-23 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_TheBloke__Wizard-Vicuna-13B-Uncensored-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TheBloke/Wizard-Vicuna-13B-Uncensored-HF在Open LLM Leaderboard上的评估过程中自动生成的。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次运行生成,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,results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还提供了如何从运行中加载数据集详细信息的示例。

该数据集是在模型TheBloke/Wizard-Vicuna-13B-Uncensored-HF在Open LLM Leaderboard上的评估过程中自动生成的。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次运行生成,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,results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还提供了如何从运行中加载数据集详细信息的示例。
提供机构:
open-llm-leaderboard-old
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/Wizard-Vicuna-13B-Uncensored-HFOpen LLM Leaderboard 上的自动创建的。

数据集结构

  • 配置数量:64个配置,每个配置对应一个评估任务。
  • 创建来源:数据集从2次运行中创建,每次运行在每个配置中作为一个特定的分割,分割名称使用运行的时间戳。
  • 最新结果:"train" 分割总是指向最新的结果。
  • 结果汇总:一个额外的配置 "results" 存储所有运行的汇总结果,用于计算和显示在 Open LLM Leaderboard 上的汇总指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TheBloke__Wizard-Vicuna-13B-Uncensored-HF", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-23T01:03:04.641003 运行的最新结果: python { "all": { "em": 0.14314177852348994, "em_stderr": 0.0035865537174832513, "f1": 0.2178586409395965, "f1_stderr": 0.003730334446277459, "acc": 0.4216675951562166, "acc_stderr": 0.00989785498376742 }, "harness|drop|3": { "em": 0.14314177852348994, "em_stderr": 0.0035865537174832513, "f1": 0.2178586409395965, "f1_stderr": 0.003730334446277459 }, "harness|gsm8k|5": { "acc": 0.08642911296436695, "acc_stderr": 0.0077400443371038056 }, "harness|winogrande|5": { "acc": 0.7569060773480663, "acc_stderr": 0.012055665630431032 } }

配置详情

以下是部分配置的详细信息:

配置列表

  • harness_arc_challenge_25

    • 分割:2023_07_18T16_17_31.150663
    • 路径:**/details_harness|arc:challenge|25_2023-07-18T16:17:31.150663.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-18T16:17:31.150663.parquet
  • harness_drop_3

    • 分割:2023_10_23T01_03_04.641003
    • 路径:**/details_harness|drop|3_2023-10-23T01-03-04.641003.parquet
    • 分割:latest
    • 路径:**/details_harness|drop|3_2023-10-23T01-03-04.641003.parquet
  • harness_gsm8k_5

    • 分割:2023_10_23T01_03_04.641003
    • 路径:**/details_harness|gsm8k|5_2023-10-23T01-03-04.641003.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2023-10-23T01-03-04.641003.parquet
  • harness_hellaswag_10

    • 分割:2023_07_18T16_17_31.150663
    • 路径:**/details_harness|hellaswag|10_2023-07-18T16:17:31.150663.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-07-18T16:17:31.150663.parquet
  • harness_hendrycksTest_5

    • 分割:2023_07_18T16_17_31.150663
    • 路径:多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T16:17:31.150663.parquet
    • 分割:latest
    • 路径:多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T16:17:31.150663.parquet

更多配置

  • harness_hendrycksTest_abstract_algebra_5
  • harness_hendrycksTest_anatomy_5
  • harness_hendrycksTest_astronomy_5
  • harness_hendrycksTest_business_ethics_5
  • harness_hendrycksTest_clinical_knowledge_5
  • harness_hendrycksTest_college_biology_5
  • harness_hendrycksTest_college_chemistry_5
  • harness_hendrycksTest_college_computer_science_5
  • harness_hendrycksTest_college_mathematics_5
  • harness_hendrycksTest_college_medicine_5
  • harness_hendrycksTest_college_physics_5
  • harness_hendrycksTest_computer_security_5
  • harness_hendrycksTest_conceptual_physics_5
  • harness_hendrycksTest_econometrics_5
  • harness_hendrycksTest_electrical_engineering_5
  • harness_hendrycksTest_elementary_mathematics_5
  • harness_hendrycksTest_formal_logic_5
  • harness_hendrycksTest_global_facts_5
  • harness_hendrycksTest_high_school_biology_5
  • harness_hendrycksTest_high_school_chemistry_5
  • harness_hendrycksTest_high_school_computer_science_5
  • harness_hendrycksTest_high_school_european_history_5
  • harness_hendrycksTest_high_school_geography_5
  • harness_hendrycksTest_high_school_government_and_politics_5
  • harness_hendrycksTest_high_school_macroeconomics_5
  • harness_hendrycksTest_high_school_mathematics_5
  • harness_hendrycksTest_high_school_microeconomics_5
  • harness_hendrycksTest_high_school_physics_5
  • harness_hendrycksTest_high_school_psychology_5
  • harness_hendrycksTest_high_school_statistics_5
  • harness_hendrycksTest_high_school_us_history_5
  • harness_hendrycksTest_high_school_world_history_5
  • harness_hendrycksTest_human_aging_5
  • harness_hendrycksTest_human_sexuality_5
  • harness_hendrycksTest_international_law_5
  • harness_hendrycksTest_jurisprudence_5
  • harness_hendrycksTest_logical_fallacies_5
  • harness_hendrycksTest_machine_learning_5
  • harness_hendrycksTest_management_5
  • harness_hendrycksTest_marketing_5
  • harness_hendrycksTest_medical_genetics_5
  • harness_hendrycksTest_miscellaneous_5
  • harness_hendrycksTest_moral_disputes_5
  • harness_hendrycksTest_moral_scenarios_5
  • harness_hendrycksTest_nutrition_5
  • harness_hendrycksTest_philosophy_5
  • harness_hendrycksTest_prehistory_5
  • harness_hendrycksTest_professional_accounting_5
  • harness_hendrycksTest_professional_law_5
  • harness_hendrycksTest_professional_medicine_5
  • harness_hendrycksTest_professional_psychology_5
  • harness_hendrycksTest_public_relations_5
  • harness_hendrycksTest_security_studies_5
  • harness_hendrycksTest_sociology_5
  • harness_hendrycksTest_us_foreign_policy_5
  • harness_hendrycksTest_virology_5
  • harness_hendrycksTest_world_religions_5
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