open-llm-leaderboard/details_AlekseyKorshuk__pygmalion-6b-vicuna-chatml
收藏Hugging Face2023-12-02 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_AlekseyKorshuk__pygmalion-6b-vicuna-chatml
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AlekseyKorshuk/pygmalion-6b-vicuna-chatml的评估运行过程中自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由5次运行生成,每次运行的结果作为特定配置中的一个分割,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,用于计算和展示在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
数据集简介
该数据集是在评估模型 AlekseyKorshuk/pygmalion-6b-vicuna-chatml 在 Open LLM Leaderboard 上的自动创建的。
数据集结构
- 配置数量:64个配置,每个配置对应一个评估任务。
- 数据来源:数据集由5次运行创建,每次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,用于计算和显示在 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_AlekseyKorshuk__pygmalion-6b-vicuna-chatml", "harness_gsm8k_5", split="train")
最新结果
以下是 最新结果 的示例: python { "all": { "acc": 0.04397270659590599, "acc_stderr": 0.005647666449126458 }, "harness|gsm8k|5": { "acc": 0.04397270659590599, "acc_stderr": 0.005647666449126458 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_07_24T10_58_39.640665
- 路径:
**/details_harness|arc:challenge|25_2023-07-24T10:58:39.640665.parquet
- 路径:
- 分割:2023_08_01T14_16_25.052724
- 路径:
**/details_harness|arc:challenge|25_2023-08-01T14:16:25.052724.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-08-01T14:16:25.052724.parquet
- 路径:
- 分割:2023_07_24T10_58_39.640665
-
harness_drop_3
- 分割:2023_09_09T13_36_28.958118
- 路径:
**/details_harness|drop|3_2023-09-09T13-36-28.958118.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|drop|3_2023-09-09T13-36-28.958118.parquet
- 路径:
- 分割:2023_09_09T13_36_28.958118
-
harness_gsm8k_5
- 分割:2023_09_09T13_36_28.958118
- 路径:
**/details_harness|gsm8k|5_2023-09-09T13-36-28.958118.parquet
- 路径:
- 分割:2023_12_02T15_52_11.848314
- 路径:
**/details_harness|gsm8k|5_2023-12-02T15-52-11.848314.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-12-02T15-52-11.848314.parquet
- 路径:
- 分割:2023_09_09T13_36_28.958118
-
harness_hellaswag_10
- 分割:2023_07_24T10_58_39.640665
- 路径:
**/details_harness|hellaswag|10_2023-07-24T10:58:39.640665.parquet
- 路径:
- 分割:2023_08_01T14_16_25.052724
- 路径:
**/details_harness|hellaswag|10_2023-08-01T14:16:25.052724.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-08-01T14:16:25.052724.parquet
- 路径:
- 分割:2023_07_24T10_58_39.640665
-
harness_hendrycksTest_5
- 分割:2023_07_24T10_58_39.640665
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-formal_logic|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-global_facts|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_biology|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_geography|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_physics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-human_aging|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-human_sexuality|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-international_law|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-jurisprudence|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-machine_learning|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-management|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-marketing|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-medical_genetics|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-miscellaneous|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-moral_disputes|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-nutrition|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-philosophy|5_2023-07-24T10:58:39.640665.parquet - 路径:
**/details_harness|hendrycksTest-prehistory|5_2023-07-24T10:58:39.640665.parquet - 路径:`**/details_harness|hendrycksTest-professional_accounting|5_2023-07-24T10
- 路径:
- 分割:2023_07_24T10_58_39.640665



