open-llm-leaderboard/details_ABX-AI__Infinite-Laymons-9B
收藏Hugging Face2024-04-10 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_ABX-AI__Infinite-Laymons-9B
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型ABX-AI/Infinite-Laymons-9B时自动创建的,评估是在Open LLM Leaderboard上进行的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割以运行的时间戳命名。train分割始终指向最新的结果。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。
该数据集是在评估模型ABX-AI/Infinite-Laymons-9B时自动创建的,评估是在Open LLM Leaderboard上进行的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割以运行的时间戳命名。train分割始终指向最新的结果。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
原始信息汇总
数据集概述
数据集名称
- pretty_name: Evaluation run of ABX-AI/Infinite-Laymons-9B
数据集描述
- dataset_summary: 该数据集是在评估模型ABX-AI/Infinite-Laymons-9B在Open LLM Leaderboard上的运行过程中自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行创建,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命名。"train"分割始终指向最新结果。此外,还有一个名为"results"的配置,存储了运行中的所有聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ABX-AI__Infinite-Laymons-9B", "harness_winogrande_5", split="train")
最新结果
- latest_results: 最新结果来自2024-04-10T11:48:19.797016的运行,包含多个任务的评估结果,如准确率(acc)、标准误差(acc_stderr)等。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_10T11_48_19.797016
- path: /details_harness|arc:challenge|25_2024-04-10T11-48-19.797016.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-10T11-48-19.797016.parquet
- split: 2024_04_10T11_48_19.797016
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_10T11_48_19.797016
- path: /details_harness|gsm8k|5_2024-04-10T11-48-19.797016.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-10T11-48-19.797016.parquet
- split: 2024_04_10T11_48_19.797016
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_10T11_48_19.797016
- path: /details_harness|hellaswag|10_2024-04-10T11-48-19.797016.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-10T11-48-19.797016.parquet
- split: 2024_04_10T11_48_19.797016
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_10T11_48_19.797016
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-10T11-48-19.797016.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-10T11-48-19.797016.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-04-10
- path:
- split: 2024_04_10T11_48_19.797016
- data_files:



