open-llm-leaderboard/details_arvindanand__Deepseek-Wizard-33B-slerp
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_arvindanand__Deepseek-Wizard-33B-slerp
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 arvindanand/Deepseek-Wizard-33B-slerp 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。数据集是从 1 次运行中创建的,每次运行作为每个配置中的一个特定分割,使用运行的时间戳命名。train 分割始终指向最新的结果。一个额外的配置 results 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。
该数据集是在模型 arvindanand/Deepseek-Wizard-33B-slerp 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。数据集是从 1 次运行中创建的,每次运行作为每个配置中的一个特定分割,使用运行的时间戳命名。train 分割始终指向最新的结果。一个额外的配置 results 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。
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 arvindanand/Deepseek-Wizard-33B-slerp
数据集来源
- dataset_summary: 该数据集是在评估模型arvindanand/Deepseek-Wizard-33B-slerp的过程中自动创建的,评估过程在Open LLM Leaderboard上进行。
数据集结构
- 组成: 由63个配置组成,每个配置对应一个评估任务。
- 创建次数: 数据集创建自1次运行。
- 数据分割: 每次运行作为一个特定的分割,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。
- 额外配置: 存在一个名为"results"的配置,存储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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_arvindanand__Deepseek-Wizard-33B-slerp", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 最新结果来自run 2024-04-10T11:55:40.376566。
- 结果内容: 包括多个任务的评估结果,如"harness|arc:challenge|25"、"harness|hellaswag|10"等,每个任务包含准确率(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_04_10T11_55_40.376566
- path: /details_harness|arc:challenge|25_2024-04-10T11-55-40.376566.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-10T11-55-40.376566.parquet
- split: 2024_04_10T11_55_40.376566
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_10T11_55_40.376566
- path: /details_harness|gsm8k|5_2024-04-10T11-55-40.376566.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-10T11-55-40.376566.parquet
- split: 2024_04_10T11_55_40.376566
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_10T11_55_40.376566
- path: /details_harness|hellaswag|10_2024-04-10T11-55-40.376566.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-10T11-55-40.376566.parquet
- split: 2024_04_10T11_55_40.376566
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_10T11_55_40.376566
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-10T11-55-40.376566.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-10T11-55-40.376566.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-10T11-55-40.376566.parquet
- path:
- split: 2024_04_10T11_55_40.376566
- data_files:



