five

open-llm-leaderboard/details_Fredithefish__Guanaco-13B-Uncensored

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_Fredithefish__Guanaco-13B-Uncensored
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/Guanaco-13B-Uncensored进行评估时自动创建的。它由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。train分割始终指向最新的结果。一个额外的配置results存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。

This dataset was automatically created during the evaluation of the model Fredithefish/Guanaco-13B-Uncensored on the Open LLM Leaderboard. It consists of 64 configurations, each corresponding to one evaluation task. The dataset is generated from two runs, where each run is represented as a specific split within each configuration. The `train` split always points to the most recent 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. This dataset can be loaded 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

该数据集是在评估模型 Fredithefish/Guanaco-13B-UncensoredOpen LLM Leaderboard 上的自动创建的。

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。
  • 额外的配置 "results" 存储所有运行结果的聚合(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_Fredithefish__Guanaco-13B-Uncensored", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-23T17:43:44.258144 运行的最新结果: python { "all": { "em": 0.0020973154362416107, "em_stderr": 0.0004685065030368403, "f1": 0.06033871644295293, "f1_stderr": 0.0013667724524043167, "acc": 0.4270991094279287, "acc_stderr": 0.009934457604610529 }, "harness|drop|3": { "em": 0.0020973154362416107, "em_stderr": 0.0004685065030368403, "f1": 0.06033871644295293, "f1_stderr": 0.0013667724524043167 }, "harness|gsm8k|5": { "acc": 0.09097801364670205, "acc_stderr": 0.00792132284401367 }, "harness|winogrande|5": { "acc": 0.7632202052091555, "acc_stderr": 0.01194759236520739 } }

配置详情

  • harness_arc_challenge_25

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|arc:challenge|25_2023-09-12T16-10-16.997512.parquet
  • harness_drop_3

    • 分割: 2023_10_23T17_43_44.258144, latest
    • 路径: **/details_harness|drop|3_2023-10-23T17-43-44.258144.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_23T17_43_44.258144, latest
    • 路径: **/details_harness|gsm8k|5_2023-10-23T17-43-44.258144.parquet
  • harness_hellaswag_10

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hellaswag|10_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: 多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-12T16-10-16.997512.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分割: 2023_09_12T16_10_16.997512, latest
    • 路径: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-12T16-10-16.997512.parquet
二维码
社区交流群
二维码
科研交流群
商业服务