open-llm-leaderboard/details_liminerity__m.star.7b
收藏Hugging Face2024-03-24 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_liminerity__m.star.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 liminerity/m.star.7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。它由 63 个配置组成,每个配置对应一个评估任务。数据集包含 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 的额外配置存储了运行的所有聚合结果,用于计算和显示 Open LLM Leaderboard 上的聚合指标。可以使用 datasets 库中的 load_dataset 函数加载该数据集。
该数据集是在模型 liminerity/m.star.7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。它由 63 个配置组成,每个配置对应一个评估任务。数据集包含 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 的额外配置存储了运行的所有聚合结果,用于计算和显示 Open LLM Leaderboard 上的聚合指标。可以使用 datasets 库中的 load_dataset 函数加载该数据集。
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 liminerity/m.star.7b
数据集描述
- dataset_summary: 该数据集是在评估模型liminerity/m.star.7b运行期间自动创建的,用于Open LLM Leaderboard。
数据集组成
- 数据结构: 包含63个配置,每个配置对应一个评估任务。
- 数据来源: 数据集由1次运行创建,每次运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳命名。
- 额外配置: “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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_liminerity__m.star.7b", "harness_winogrande_5", split="train")
最新结果
- 结果来源: latest results from run 2024-03-24T15:13:30.974965
- 结果内容: 包含多个任务的准确率(acc)、标准误差(acc_stderr)等指标。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_03_24T15_13_30.974965
- path: /details_harness|arc:challenge|25_2024-03-24T15-13-30.974965.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-24T15-13-30.974965.parquet
- split: 2024_03_24T15_13_30.974965
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_24T15_13_30.974965
- path: /details_harness|gsm8k|5_2024-03-24T15-13-30.974965.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-24T15-13-30.974965.parquet
- split: 2024_03_24T15_13_30.974965
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_24T15_13_30.974965
- path: /details_harness|hellaswag|10_2024-03-24T15-13-30.974965.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-24T15-13-30.974965.parquet
- split: 2024_03_24T15_13_30.974965
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_24T15_13_30.974965
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-international_law|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-management|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-marketing|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-sociology|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-virology|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-03-24T15-13-30.974965.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-24T15-13-30.974965.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-24T15-13-30.974965.parquet
- **/details_harness|hendrycksTest-business_ethics|5_
- path:
- split: 2024_03_24T15_13_30.974965
- data_files:



