jondurbin/airoboros-3.0
收藏数据集概述
该数据集是airoboros数据集的延续,主要新增了以下两个部分:
- MathJSON:包含数学问题,以“Create a MathJSON solution to the following:”为前缀,输出一个位于
<mathjson>和</mathjson>标签之间的JSON,可被解析并通过确定性库执行计算。 - 匿名贡献的RP数据集:用于增强多轮对话的连贯性。
部分MathJSON数据改编自https://huggingface.co/datasets/meta-math/MetaMathQA。
格式
数据集采用ShareGPT格式,以更好地适应OS生态系统的微调工具。
MathJSON
数学对大型语言模型(LLMs)来说非常困难,尤其是浮点运算、三角函数、阶乘和多位数运算。
与其向LLM发送数百万个示例进行微调,不如创建一个新的mathjson类别,将问题的解决方案简单地表示为一个可由传统计算评估的JSON字符串。
数据集包含约4000个样本,作为概念验证。现在微调模型已经基本理解了如何表示问题,可以很容易地扩展。
例如:
Create a MathJSON solution to the following: Calculate the area of a circle with radius of 17.2456cm. Include your reasoning. [/INST]
The area (A) of a circle is given by the formula A = πr², where r is the radius of the circle. Since the radius is given in centimeters, we need to convert it to meters first. We know that 1 meter equals 100 centimeters. Therefore, we can represent the radius as: r = 17.2456 cm * 100/1.
Once we have the radius in meters, we can calculate the area of the circle using the formula A = πr².
Solution as MathJSON: <mathjson> [ "Multiply", "Pi", [ "Power", 17.2456, 2 ] ] </mathjson>
只需提取<mathjson>标签之间的JSON字符串,并使用https://cortexjs.io/compute-engine/或我的功能有限的Python版本进行评估https://github.com/jondurbin/airoboros/blob/mathjson/airoboros/mathjson.py。



