five

GEM/references

收藏
Hugging Face2022-06-23 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/GEM/references
下载链接
链接失效反馈
官方服务:
资源简介:
# GEM References ## What is it? This repository contains all the reference datasets that are used for running evaluation on the GEM benchmark. Some of these datasets were originally hosted as a [GitHub release](https://github.com/GEM-benchmark/GEM-metrics/releases) on the [`GEM-metrics`](https://github.com/GEM-benchmark/GEM-metrics) repository, but have been migrated to the Hugging Face Hub. ## Converting datasets to JSON We provide a `convert_dataset_to_json.py` conversion script that converts the datasets in the GEM organisation to the JSON format expected by the `GEM-metrics` library. To run the script, first install [`jq`](https://stedolan.github.io/jq/download/) and then install the script's Python dependencies: ``` python -m pip install -r requirements.txt ``` You can then run the script as follows: ```python python generate_evaluation_datasets.py ``` This script will: * Download and convert the datasets under the GEM organisation to JSON format * Validate that the each dataset has the expected columns of `gem_id`, `target`, and `references`
提供机构:
GEM
原始信息汇总

GEM References 数据集概述

数据集用途

该数据集用于GEM基准的评估运行,包含所有参考数据集。

数据集格式转换

提供了一个名为convert_dataset_to_json.py的转换脚本,用于将GEM组织下的数据集转换为GEM-metrics库预期的JSON格式。

转换步骤

  1. 安装jq工具。

  2. 安装脚本的Python依赖:

    python -m pip install -r requirements.txt

  3. 运行脚本: python python generate_evaluation_datasets.py

脚本功能

  • 下载并转换GEM组织下的数据集至JSON格式。
  • 验证每个数据集是否包含预期的gem_id, target, 和 references列。
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作