neovalle/H4rmony_dpo
收藏Hugging Face2024-02-05 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/neovalle/H4rmony_dpo
下载链接
链接失效反馈官方服务：
资源简介：
---
license: mit
task_categories:
- question-answering
- text-classification
- reinforcement-learning
- text-generation
tags:
- ecolinguistics
- ecology
- sustainability
- environment
- synthetic
size_categories:
- 1K<n<10K
---
This dataset is based on [neovalle/H4rmony](https://huggingface.co/datasets/neovalle/H4rmony), and optimised to the format required by DPOTrainer from the trl library.
提供机构：
neovalle
原始信息汇总
数据集概述
数据集来源
- 基于
neovalle/H4rmony数据集。
数据集优化
- 优化格式以适配
trl库中的DPOTrainer要求。
