open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1

Name: open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1
Creator: open-llm-leaderboard
Published: 2023-10-22 14:08:34
License: 暂无描述

Hugging Face2023-10-22 更新2024-03-04 收录

下载链接：

https://hf-mirror.com/datasets/open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1

下载链接

链接失效反馈

官方服务：

资源简介：

--- pretty_name: Evaluation run of yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1](https://huggingface.co/yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1)\ \ on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 3 configuration, each one coresponding to one of the\ \ evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be\ \ found as a specific split in each configuration, the split being named using the\ \ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\ \nAn additional configuration \"results\" store all the aggregated results of the\ \ run (and is used to compute and display the agregated metrics on the [Open LLM\ \ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\ \nTo load the details from a run, you can for instance do the following:\n```python\n\ from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2023-10-22T14:08:24.468600](https://huggingface.co/datasets/open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1/blob/main/results_2023-10-22T14-08-24.468600.json)(note\ \ that their might be results for other tasks in the repos if successive evals didn't\ \ cover the same tasks. You find each in the results and the \"latest\" split for\ \ each eval):\n\n```python\n{\n \"all\": {\n \"em\": 0.005138422818791947,\n\ \ \"em_stderr\": 0.0007322104102794228,\n \"f1\": 0.07932466442953026,\n\ \ \"f1_stderr\": 0.0017316010986472678,\n \"acc\": 0.4421008477279133,\n\ \ \"acc_stderr\": 0.010182910924383982\n },\n \"harness|drop|3\": {\n\ \ \"em\": 0.005138422818791947,\n \"em_stderr\": 0.0007322104102794228,\n\ \ \"f1\": 0.07932466442953026,\n \"f1_stderr\": 0.0017316010986472678\n\ \ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.10993176648976498,\n \ \ \"acc_stderr\": 0.008616195587865416\n },\n \"harness|winogrande|5\"\ : {\n \"acc\": 0.7742699289660616,\n \"acc_stderr\": 0.011749626260902547\n\ \ }\n}\n```" repo_url: https://huggingface.co/yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard point_of_contact: clementine@hf.co configs: - config_name: harness_drop_3 data_files: - split: 2023_10_19T17_39_53.818572 path: - '**/details_harness|drop|3_2023-10-19T17-39-53.818572.parquet' - split: 2023_10_22T14_08_24.468600 path: - '**/details_harness|drop|3_2023-10-22T14-08-24.468600.parquet' - split: latest path: - '**/details_harness|drop|3_2023-10-22T14-08-24.468600.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_10_19T17_39_53.818572 path: - '**/details_harness|gsm8k|5_2023-10-19T17-39-53.818572.parquet' - split: 2023_10_22T14_08_24.468600 path: - '**/details_harness|gsm8k|5_2023-10-22T14-08-24.468600.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-10-22T14-08-24.468600.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_10_19T17_39_53.818572 path: - '**/details_harness|winogrande|5_2023-10-19T17-39-53.818572.parquet' - split: 2023_10_22T14_08_24.468600 path: - '**/details_harness|winogrande|5_2023-10-22T14-08-24.468600.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-10-22T14-08-24.468600.parquet' - config_name: results data_files: - split: 2023_10_19T17_39_53.818572 path: - results_2023-10-19T17-39-53.818572.parquet - split: 2023_10_22T14_08_24.468600 path: - results_2023-10-22T14-08-24.468600.parquet - split: latest path: - results_2023-10-22T14-08-24.468600.parquet --- # Dataset Card for Evaluation run of yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 - **Paper:** - **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard - **Point of Contact:** clementine@hf.co ### Dataset Summary Dataset automatically created during the evaluation run of model [yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1](https://huggingface.co/yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 3 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the agregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)). To load the details from a run, you can for instance do the following: ```python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2023-10-22T14:08:24.468600](https://huggingface.co/datasets/open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1/blob/main/results_2023-10-22T14-08-24.468600.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval): ```python { "all": { "em": 0.005138422818791947, "em_stderr": 0.0007322104102794228, "f1": 0.07932466442953026, "f1_stderr": 0.0017316010986472678, "acc": 0.4421008477279133, "acc_stderr": 0.010182910924383982 }, "harness|drop|3": { "em": 0.005138422818791947, "em_stderr": 0.0007322104102794228, "f1": 0.07932466442953026, "f1_stderr": 0.0017316010986472678 }, "harness|gsm8k|5": { "acc": 0.10993176648976498, "acc_stderr": 0.008616195587865416 }, "harness|winogrande|5": { "acc": 0.7742699289660616, "acc_stderr": 0.011749626260902547 } } ``` ### Supported Tasks and Leaderboards [More Information Needed] ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed]

# yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 模型评估运行数据集卡片 ## 数据集描述 - **主页：** - **仓库：** https://huggingface.co/yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 - **论文：** - **排行榜：** [开放大语言模型排行榜（Open LLM Leaderboard）](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) - **联系人：** clementine@hf.co ### 数据集摘要本数据集为模型**yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1**在开放大语言模型排行榜上开展评估运行期间自动生成。本数据集包含3个配置项，每个配置项对应一项评估任务。本数据集源自2次评估运行，每次运行均可在各配置项下找到对应的拆分，拆分名称以运行的时间戳命名。其中"train"拆分始终指向最新的评估结果。额外增设的"results"配置项可存储所有评估运行的聚合结果，用于在开放大语言模型排行榜上计算并展示聚合评测指标。如需加载某次运行的详细数据，可参考如下示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1", "harness_winogrande_5", split="train") ## 最新评测结果以下为2023-10-22T14:08:24.468600运行的最新结果（[点击查看详情](https://huggingface.co/datasets/open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1/blob/main/results_2023-10-22T14-08-24.468600.json)）。注：若后续的评估运行未覆盖全部任务，则仓库中可能存在其他任务的评测结果，你可在各评估运行的"results"和"latest"拆分中找到对应内容： python { "all": { "em": 0.005138422818791947, "em_stderr": 0.0007322104102794228, "f1": 0.07932466442953026, "f1_stderr": 0.0017316010986472678, "acc": 0.4421008477279133, "acc_stderr": 0.010182910924383982 }, "harness|drop|3": { "em": 0.005138422818791947, "em_stderr": 0.0007322104102794228, "f1": 0.07932466442953026, "f1_stderr": 0.0017316010986472678 }, "harness|gsm8k|5": { "acc": 0.10993176648976498, "acc_stderr": 0.008616195587865416 }, "harness|winogrande|5": { "acc": 0.7742699289660616, "acc_stderr": 0.011749626260902547 } } ### 支持的任务与排行榜 [需要更多信息] ### 语言 [需要更多信息] ## 数据集结构 ### 数据实例 [需要更多信息] ### 数据字段 [需要更多信息] ### 数据拆分 [需要更多信息] ## 数据集创建 ### 筛选依据 [需要更多信息] ### 源数据 #### 初始数据收集与归一化 [需要更多信息] #### 源语言生成者是谁？ [需要更多信息] ### 标注 #### 标注流程 [需要更多信息] #### 标注者是谁？ [需要更多信息] ### 个人与敏感信息 [需要更多信息] ## 数据使用注意事项 ### 数据集的社会影响 [需要更多信息] ### 偏差讨论 [需要更多信息] ### 其他已知限制 [需要更多信息] ## 附加信息 ### 数据集策展人 [需要更多信息] ### 许可信息 [需要更多信息] ### 引用信息 [需要更多信息] ### 贡献 [需要更多信息]

提供机构：

open-llm-leaderboard

原始信息汇总

数据集卡片 for Evaluation run of yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1

数据集描述

数据集概述

该数据集是在模型 yeontaek/Platypus2xOpenOrca-13B-IA3-v2.1 的评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集由3个配置组成，每个配置对应一个评估任务。

数据集从2次运行中创建。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。

一个额外的配置 "results" 存储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）。

加载运行细节的示例如下： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3-v2.1", "harness_winogrande_5", split="train")