open-llm-leaderboard/details_weezywitasneezy__OxytocinErosEngineeringFX-7B-slerp
收藏Hugging Face2024-04-08 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_weezywitasneezy__OxytocinErosEngineeringFX-7B-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Open LLM Leaderboard上对模型weezywitasneezy/OxytocinErosEngineeringFX-7B-slerp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,运行的时间戳作为分割的名称。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,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weezywitasneezy/OxytocinErosEngineeringFX-7B-slerp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,运行的时间戳作为分割的名称。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,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 weezywitasneezy/OxytocinErosEngineeringFX-7B-slerp
数据集创建
- dataset_summary: 该数据集是在评估模型weezywitasneezy/OxytocinErosEngineeringFX-7B-slerp的过程中自动创建的,评估平台为Open LLM Leaderboard。
数据集组成
- 配置数量: 63个配置,每个配置对应一个评估任务。
- 数据集创建次数: 1次运行。
- 数据集结构: 每个运行被视为一个特定的分割,分割名称使用运行的时间戳命名。"train"分割始终指向最新的结果。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_weezywitasneezy__OxytocinErosEngineeringFX-7B-slerp", "harness_winogrande_5", split="train")
最新结果
- 最新结果存储在名为"results"的配置中,用于计算和显示Open LLM Leaderboard上的聚合指标。
数据集详细配置
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_08T22_29_42.505873
- path: /details_harness|arc:challenge|25_2024-04-08T22-29-42.505873.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-08T22-29-42.505873.parquet
- split: 2024_04_08T22_29_42.505873
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_08T22_29_42.505873
- path: /details_harness|gsm8k|5_2024-04-08T22-29-42.505873.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-08T22-29-42.505873.parquet
- split: 2024_04_08T22_29_42.505873
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_08T22_29_42.505873
- path: /details_harness|hellaswag|10_2024-04-08T22-29-42.505873.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-08T22-29-42.505873.parquet
- split: 2024_04_08T22_29_42.505873
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_08T22_29_42.505873
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-08T22-29-42.505873.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-08T22-29-42.505873.parquet
- **/details_harness|hendrycksTest-global
- path:
- split: 2024_04_08T22_29_42.505873
- data_files:



