open-llm-leaderboard-old/details_Inv__Kazbek-7B
收藏Hugging Face2024-03-27 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Inv__Kazbek-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Open LLM Leaderboard上对模型Inv/Kazbek-7B进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到,分割以运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在Open LLM Leaderboard上对模型Inv/Kazbek-7B进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到,分割以运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集简介
该数据集是在对模型Inv/Kazbek-7B进行评估运行期间自动创建的,用于Open LLM Leaderboard。数据集包含63个配置,每个配置对应一个评估任务。
数据集结构
数据集由1次运行创建,每个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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Inv__Kazbek-7B", "harness_winogrande_5", split="train")
最新结果
这些是最新结果,来自2024-03-27T19:02:48.709796的运行。每个任务的结果可以在"results"配置和每个评估的"latest"分割中找到。
配置详情
-
config_name: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_27T19_02_48.709796
- 路径:
**/details_harness|arc:challenge|25_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: 2024_03_27T19_02_48.709796
- 数据文件:
-
config_name: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_27T19_02_48.709796
- 路径:
**/details_harness|gsm8k|5_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|gsm8k|5_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: 2024_03_27T19_02_48.709796
- 数据文件:
-
config_name: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_27T19_02_48.709796
- 路径:
**/details_harness|hellaswag|10_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|hellaswag|10_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: 2024_03_27T19_02_48.709796
- 数据文件:
-
config_name: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_27T19_02_48.709796
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-27T19-02-48.709796.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-27T19-02-48.709796.parquet
- 路径:
- 分割: 2024_03_27T19_02_48.709796
- 数据文件:



