我可以为OpenAI API Codex模型创建微调模型吗？

发布于 2025-01-22 02:27:06 字数 435 浏览 0 评论 0原文

我想将用户请求转换为某种结构化数据格式的门票，例如JSON。例如：

用户：我想订购两把椅子和一张桌子，左侧有三个抽屉。
输出：

{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}

看起来GPT-3本身并不适合此任务，因为输出不采用自然语言的形式，但是法典可能是吗？但是我在OpenAI API文档中找不到（如果有可能的话？）如何为OpenAI API Codex模型创建自定义 /微调模型？

原文

I'd like to translate user requests into tickets in some sort of structured data format, e.g. JSON. For example:

User: I want to order two chairs and a desk with three drawers on the left side.
Output:

{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}

It looks like GPT-3 itself is not very-well suited for this task, because output is not in the form of natural language, however Codex might be? But I can't find in OpenAI API docs how I can (if it's possible at all?) to create a custom / fine-tuned model for OpenAI API Codex models?

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

￡烟消云散 2025-01-29 02:27:06

@xara Codex不支持一种微调其模型的方法。

您能做的就是迅速工程。

为模型提供一些演示，并尝试使用Codex是否可以通过预期的输出来渗透您。

回复收藏 0 原文

苦笑流年记忆 2025-01-29 02:27:06

如果您的JSON不太参与，您可能只需要及时的创意工程即可。在此示例中，我首先给您的提示，以显示标准输入和响应，然后将其设置为完成任务。这是我使用的确切提示：

Please complete the following:
User: I want to order two chairs and a desk with three drawers on the left side.
Output:
```json
{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}
```
User: I want three chairs and a desk with 2 drawers on the left and a desk with 3 drawers on the right.
Output:
```

请注意，我以三个刻度标记结束，以表明它应该立即以代码

chatgpt开始返回以下内容：

{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 2, "position": "left" }] },
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "right" }] },
        { "type": "chair", "qty": 3 }
    ]
}

If your JSON is not too involved, you may simply need creative prompt engineering. In this example, I started by giving ChatGPT your prompt to show a standard input and response and then set it up as a completion task. This is the exact prompt I used:

Please complete the following:
User: I want to order two chairs and a desk with three drawers on the left side.
Output:
```json
{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "left" }] },
        { "type": "chair", "qty": 2 }
    ]
}
```
User: I want three chairs and a desk with 2 drawers on the left and a desk with 3 drawers on the right.
Output:
```

Note that I concluded with three tick marks to indicate that it should immediately begin with the code

ChatGPT returned the following:

{
    "type": "furniture",
    "items": [
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 2, "position": "left" }] },
        { "type": "desk", "qty": 1, "included_items": [{ "type": "drawer", "qty": 3, "position": "right" }] },
        { "type": "chair", "qty": 3 }
    ]
}

回复收藏 0 原文