open-llm-leaderboard/details_Kukedlc__NeuralSynthesis-7B-v0.2
收藏Hugging Face2024-04-06 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Kukedlc__NeuralSynthesis-7B-v0.2
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Kukedlc/NeuralSynthesis-7B-v0.2在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集包含一次运行的结果,每次运行都作为一个特定的分割,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。一个名为results的额外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还提供了如何使用Hugging Face datasets库加载数据集的示例。
该数据集是在模型Kukedlc/NeuralSynthesis-7B-v0.2在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集包含一次运行的结果,每次运行都作为一个特定的分割,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。一个名为results的额外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还提供了如何使用Hugging Face datasets库加载数据集的示例。
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 Kukedlc/NeuralSynthesis-7B-v0.2
数据集描述
- dataset_summary: 该数据集是在评估模型Kukedlc/NeuralSynthesis-7B-v0.2运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集来源于1次运行,每次运行都有特定的分割,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。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Kukedlc__NeuralSynthesis-7B-v0.2", "harness_winogrande_5", split="train")
最新结果
- latest_results: 最新结果来自2024-04-06T18:31:25.878495的运行,包含多个任务的准确率(acc)和标准误差(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_04_06T18_31_25.878495
- path: /details_harness|arc:challenge|25_2024-04-06T18-31-25.878495.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-06T18-31-25.878495.parquet
- split: 2024_04_06T18_31_25.878495
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_06T18_31_25.878495
- path: /details_harness|gsm8k|5_2024-04-06T18-31-25.878495.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-06T18-31-25.878495.parquet
- split: 2024_04_06T18_31_25.878495
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_06T18_31_25.878495
- path: /details_harness|hellaswag|10_2024-04-06T18-31-25.878495.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-06T18-31-25.878495.parquet
- split: 2024_04_06T18_31_25.878495
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_06T18_31_25.878495
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-international_law|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-management|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-marketing|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-sociology|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-virology|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-04-06T18-31-25.878495.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-06T18-31-25.878495.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-06T18-31-25.878495.parquet
- **/details_harness|hendrycksTest-college_biology|
- path:
- split: 2024_04_06T18_31_25.878495
- data_files:
搜集汇总
数据集介绍

以上内容由遇见数据集搜集并总结生成



