open-llm-leaderboard-old/details_mlabonne__Beyonder-4x7B-v3
收藏数据集概述
数据集简介
该数据集是在评估模型 mlabonne/Beyonder-4x7B-v3 在 Open LLM Leaderboard 上的自动创建的。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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_mlabonne__Beyonder-4x7B-v3", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要:
python { "all": { "acc": 0.6545651435392091, "acc_stderr": 0.0321355052869314, "acc_norm": 0.6539201029549403, "acc_norm_stderr": 0.032807725306125385, "mc1": 0.5887392900856793, "mc1_stderr": 0.017225627083660874, "mc2": 0.7444087204884349, "mc2_stderr": 0.014280260468011773 }, "harness|arc:challenge|25": { "acc": 0.697098976109215, "acc_stderr": 0.013428241573185349, "acc_norm": 0.7167235494880546, "acc_norm_stderr": 0.013167478735134575 }, "harness|hellaswag|10": { "acc": 0.7144991037641903, "acc_stderr": 0.004507296196227808, "acc_norm": 0.888568014339773, "acc_norm_stderr": 0.0031402323925687967 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_03_22T12_17_08.484037
- path: **/details_harness|arc:challenge|25_2024-03-22T12-17-08.484037.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-03-22T12-17-08.484037.parquet
- split: 2024_03_22T12_17_08.484037
-
config_name: harness_gsm8k_5
- split: 2024_03_22T12_17_08.484037
- path: **/details_harness|gsm8k|5_2024-03-22T12-17-08.484037.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-03-22T12-17-08.484037.parquet
- split: 2024_03_22T12_17_08.484037
-
config_name: harness_hellaswag_10
- split: 2024_03_22T12_17_08.484037
- path: **/details_harness|hellaswag|10_2024-03-22T12-17-08.484037.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-03-22T12-17-08.484037.parquet
- split: 2024_03_22T12_17_08.484037
-
config_name: harness_hendrycksTest_5
- split: 2024_03_22T12_17_08.484037
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-22T12-17-08.484037.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-22T12-17-08.484037.parquet
其他文件路径...
- path:
- split: 2024_03_22T12_17_08.484037
}



