open-llm-leaderboard/details_LeroyDyer__Mixtral_Chat_X_128k
收藏Hugging Face2024-03-22 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_LeroyDyer__Mixtral_Chat_X_128k
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LeroyDyer/Mixtral_Chat_X_128k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的额外配置存储了所有运行的聚合结果,这些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`datasets`库中的`load_dataset`函数加载数据集的示例。
该数据集是在模型LeroyDyer/Mixtral_Chat_X_128k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的额外配置存储了所有运行的聚合结果,这些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`datasets`库中的`load_dataset`函数加载数据集的示例。
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 LeroyDyer/Mixtral_Chat_X_128k
数据集创建
- dataset_summary: 该数据集是在评估模型LeroyDyer/Mixtral_Chat_X_128k的过程中自动创建的,该模型在Open LLM Leaderboard上进行评估。
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: 从1次运行中创建
- 数据集分割: 每个配置中有一个特定的分割,以运行的时间戳命名。"train"分割始终指向最新结果。
额外配置
- 配置名称: "results"
- 功能: 存储所有运行结果的聚合数据,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_LeroyDyer__Mixtral_Chat_X_128k", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 来自2024-03-22T00:31:04.387886的运行
- 结果内容: 包含多个任务的评估结果,每个任务有相应的准确率(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_03_22T00_31_04.387886
- path: /details_harness|arc:challenge|25_2024-03-22T00-31-04.387886.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-22T00-31-04.387886.parquet
- split: 2024_03_22T00_31_04.387886
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_22T00_31_04.387886
- path: /details_harness|gsm8k|5_2024-03-22T00-31-04.387886.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-22T00-31-04.387886.parquet
- split: 2024_03_22T00_31_04.387886
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_22T00_31_04.387886
- path: /details_harness|hellaswag|10_2024-03-22T00-31-04.387886.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-22T00-31-04.387886.parquet
- split: 2024_03_22T00_31_04.387886
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_22T00_31_04.387886
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-22T00-31-04.387886.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-22T00-31-04.387886.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-22T00-31-04.387886.parquet
- path:
- split: 2024_03_22T00_31_04.387886
- data_files:



