open-llm-leaderboard/details_hamxea__Llama-2-7b-chat-hf-activity-fine-tuned-v4
收藏Hugging Face2024-03-31 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_hamxea__Llama-2-7b-chat-hf-activity-fine-tuned-v4
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hamxea/Llama-2-7b-chat-hf-activity-fine-tuned-v4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。数据集由2次运行生成,每次运行的结果存储在不同的分割中,分割名称使用运行的时间戳命名。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,用于在Open LLM Leaderboard上计算和显示聚合指标。
该数据集是在Open LLM Leaderboard上对模型hamxea/Llama-2-7b-chat-hf-activity-fine-tuned-v4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。数据集由2次运行生成,每次运行的结果存储在不同的分割中,分割名称使用运行的时间戳命名。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,用于在Open LLM Leaderboard上计算和显示聚合指标。
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 hamxea/Llama-2-7b-chat-hf-activity-fine-tuned-v4
数据集描述
- dataset_summary: 该数据集是在评估模型hamxea/Llama-2-7b-chat-hf-activity-fine-tuned-v4的过程中自动创建的,评估在Open LLM Leaderboard上进行。
数据集组成
- 数据结构: 包含63个配置,每个配置对应一个评估任务。
- 数据来源: 数据集由2次运行创建,每次运行对应一个特定的分割,分割名称使用运行的时间戳命名。
- 特殊配置: “results”配置存储所有运行的聚合结果,用于计算和显示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_hamxea__Llama-2-7b-chat-hf-activity-fine-tuned-v4", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 来自2024-03-31T18:33:35.231026的运行。
- 结果内容: 包含多个任务的评估结果,如准确率(acc)、标准误差(acc_stderr)等。
数据集配置详情
配置列表
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_03_31T18_32_16.094801
- path: /details_harness|arc:challenge|25_2024-03-31T18-32-16.094801.parquet
- split: 2024_03_31T18_33_35.231026
- path: /details_harness|arc:challenge|25_2024-03-31T18-33-35.231026.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-31T18-33-35.231026.parquet
- split: 2024_03_31T18_32_16.094801
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_31T18_32_16.094801
- path: /details_harness|gsm8k|5_2024-03-31T18-32-16.094801.parquet
- split: 2024_03_31T18_33_35.231026
- path: /details_harness|gsm8k|5_2024-03-31T18-33-35.231026.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-31T18-33-35.231026.parquet
- split: 2024_03_31T18_32_16.094801
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_31T18_32_16.094801
- path: /details_harness|hellaswag|10_2024-03-31T18-32-16.094801.parquet
- split: 2024_03_31T18_33_35.231026
- path: /details_harness|hellaswag|10_2024-03-31T18-33-35.231026.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-31T18-33-35.231026.parquet
- split: 2024_03_31T18_32_16.094801
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_31T18_32_16.094801
- path: /details_harness|hendrycksTest-abstract_algebra|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-anatomy|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-astronomy|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-business_ethics|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-college_biology|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-college_chemistry|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-college_computer_science|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-college_mathematics|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-college_medicine|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-college_physics|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-computer_security|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-conceptual_physics|5_2024-03-31T18-32-16.094801.parquet
- path: /details_harness|hendrycksTest-econometrics|5_2024-03-31T18-32-16.094801.parquet
- split: 2024_03_31T18_32_16.094801
- data_files:



