Encoding issues on OpenAI predictions after fine-tuning

题意：“微调后 OpenAI 预测的编码问题”

问题背景：

I'm following this OpenAI tutorial about fine-tuning.

“我正在按照这个 OpenAI 微调教程进行操作。”

I already generated the dataset with the openai tool. The problem is that the outputs encoding (inference result) is mixing UTF-8 with non UTF-8 characters.

“我已经使用 OpenAI 工具生成了数据集。问题在于输出编码（推理结果）混合了 UTF-8 和非 UTF-8 字符。”

The generated model looks like this:        “生成的模型看起来像这样:”

{"prompt":"Usuario: Quién eres\\nAsistente:","completion":" Soy un Asisten