py-dpo-v0.1

### Overview

DPO dataset meant to enhance python coding abilities.

This dataset uses the excellent https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca dataset as the "chosen" responses, given this dataset was already tested and validated.

The "rejected" values were generated with a mix of airoboros-l2-13b-3.1 and bagel-7b-v0.1.

The rejected values may actually be perfectly fine, but the assumption here is that the values are generally a lower quality than the chosen counterpart. Items with duplicate code blocks were removed.

### Contribute

If you're interested in new functionality/datasets, take a look at [bagel repo](https://github.com/jondurbin/bagel) and [airoboros](https://github.com/jondurbin/airoboros) and either make a PR or open an issue with details.

To help me with the fine-tuning costs, dataset generation, etc., please use one of the following:

- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf

### 概述
本DPO数据集旨在提升Python编程能力。
本数据集采用已通过充分测试与验证的优质数据集https://huggingface.co/datasets/Vezora/Tested-22k-Python-Alpaca作为「优选」回复样本，因该数据集已完成全面的测试与校验。
「非优选」样本由airoboros-l2-13b-3.1与bagel-7b-v0.1两款模型混合生成。
尽管非优选样本本身可能并无明显缺陷，但本数据集默认其整体质量劣于对应的优选样本。已移除包含重复代码块的数据条目。

### 贡献
若您对新增功能或数据集感兴趣，可访问[bagel代码仓库](https://github.com/jondurbin/bagel)与[airoboros仓库](https://github.com/jondurbin/airoboros)，通过提交拉取请求（PR）或详细开启议题的方式参与贡献。
若您愿意支持微调成本、数据集生成等相关工作，可通过以下渠道进行捐助：
- https://bmc.link/jondurbin
- 以太坊地址：0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- 比特币地址：bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf