open-llm-leaderboard-old/details_Badgids__Gonzo-Chat-7B
收藏Hugging Face2024-03-02 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Badgids__Gonzo-Chat-7B
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Badgids/Gonzo-Chat-7B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。数据集是从1次运行中创建的,每次运行在每个配置中作为一个特定的分割存在。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。README文件还提供了如何加载运行中的详细信息的说明,并提供了特定运行的最新结果。
该数据集是在Open LLM Leaderboard上对模型Badgids/Gonzo-Chat-7B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。数据集是从1次运行中创建的,每次运行在每个配置中作为一个特定的分割存在。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。README文件还提供了如何加载运行中的详细信息的说明,并提供了特定运行的最新结果。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集简介
该数据集是在对模型 Badgids/Gonzo-Chat-7B 进行评估运行期间自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建,每个运行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。
额外配置
一个额外的配置 "results" 存储所有运行的聚合结果,用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Badgids__Gonzo-Chat-7B", "harness_winogrande_5", split="train")
最新结果
这些是最新结果(来自 2024-03-02T19:13:21.231650 运行),包含各个任务的准确率和标准误差。
配置详情
以下是部分配置及其数据文件路径:
-
config_name: harness_arc_challenge_25
- split: 2024_03_02T19_13_21.231650
- path: **/details_harness|arc:challenge|25_2024-03-02T19-13-21.231650.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-03-02T19-13-21.231650.parquet
- split: 2024_03_02T19_13_21.231650
-
config_name: harness_gsm8k_5
- split: 2024_03_02T19_13_21.231650
- path: **/details_harness|gsm8k|5_2024-03-02T19-13-21.231650.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-03-02T19-13-21.231650.parquet
- split: 2024_03_02T19_13_21.231650
-
config_name: harness_hellaswag_10
- split: 2024_03_02T19_13_21.231650
- path: **/details_harness|hellaswag|10_2024-03-02T19-13-21.231650.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-03-02T19-13-21.231650.parquet
- split: 2024_03_02T19_13_21.231650
-
config_name: harness_hendrycksTest_5
- split: 2024_03_02T19_13_21.231650
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-02T19-13-21.231650.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-02T19-13-21.231650.parquet
- path:
- split: 2024_03_02T19_13_21.231650



