open-llm-leaderboard/details_Gille__StrangeMerges_53-7B-model_stock
收藏Hugging Face2024-04-02 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Gille__StrangeMerges_53-7B-model_stock
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Gille/StrangeMerges_53-7B-model_stock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。数据集是从1次运行中创建的,每次运行都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。train分割始终指向最新的结果。此外,还有一个名为results的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。
该数据集是在模型Gille/StrangeMerges_53-7B-model_stock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。数据集是从1次运行中创建的,每次运行都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。train分割始终指向最新的结果。此外,还有一个名为results的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 Gille/StrangeMerges_53-7B-model_stock
数据集描述
- dataset_summary: 该数据集是在评估模型Gille/StrangeMerges_53-7B-model_stock时自动创建的,用于Open LLM Leaderboard。
数据集组成
- 配置数量: 63个
- 每个配置对应一个评估任务
- 数据集来源: 1个运行
- 数据集结构: 每个运行作为一个特定的分割,分割名称使用运行的时间戳。"train"分割始终指向最新结果。
- 额外配置: "results",存储所有运行的聚合结果,用于计算和显示聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Gille__StrangeMerges_53-7B-model_stock", "harness_winogrande_5", split="train")
最新结果
- 结果来源: latest results from run 2024-04-02T22:26:33.194666
- 注意: 可能存在其他任务的结果,每个任务在"results"和"latest"分割中均有记录。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_02T22_26_33.194666
- path: /details_harness|arc:challenge|25_2024-04-02T22-26-33.194666.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-04-02T22-26-33.194666.parquet
- split: 2024_04_02T22_26_33.194666
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_02T22_26_33.194666
- path: /details_harness|gsm8k|5_2024-04-02T22-26-33.194666.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-04-02T22-26-33.194666.parquet
- split: 2024_04_02T22_26_33.194666
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_02T22_26_33.194666
- path: /details_harness|hellaswag|10_2024-04-02T22-26-33.194666.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-04-02T22-26-33.194666.parquet
- split: 2024_04_02T22_26_33.194666
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_02T22_26_33.194666
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-02T22-26-33.194666.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-02T22-26-33.194666.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024
- path:
- split: 2024_04_02T22_26_33.194666
- data_files:



