openai-api - OpenAI ChatGPT (GPT-3.5) API : Can I use a fine-tuned GPT-3 model with the GPT-3. 5 API 端点(错误 : "Invalid URL (POST/v1/chat/completions)")?

Question

创建微调模型后，如何在/v1/chat/completions 中使用它？我们尝试了这个，但出现了错误

curl --location 'https://api.openai.com/v1/chat/completions' \
--header 'Authorization: Bearer TOKEN' \
--header 'Content-Type: application/json' \
--data '{
    "model": "davinci:ft-xxx-inc:6302f74d2000001f00f80919-2023-04-15-00-47-48",
    "messages": [
        {
            "role": "user",
            "content": "How to use apple vision api to recognize text? any example?"
        }
    ]
}'
// Error
{
    "error": {
        "message": "Invalid URL (POST /v1/chat/completions)",
        "type": "invalid_request_error",
        "param": null,
        "code": null
    }
}

Answer 1

您似乎想微调 GPT-3 davinci模型并将其与 GPT-3.5 API 端点一起使用。

您可以微调 davinci型号如官方所述OpenAI documentation :

Fine-tuning is currently only available for the following base models:davinci, curie, babbage, and ada. These are the original models thatdo not have any instruction following training (like text-davinci-003does for example). You are also able to continue fine-tuning afine-tuned model to add additional data without having to start fromscratch.

但是... davinci型号与 /v1/chat/completions 不兼容API端点如官方OpenAI documentation中所述:

<表类=“s-表”><标题>端点型号名称 <正文>/v1/chat/completionsgpt-4、gpt-4-0613、gpt-4-32k、gpt-4-32k-0613、gpt-3.5-turbo、gpt-3.5-turbo-0613、gpt-3.5-turbo-16k、gpt -3.5-turbo-16k-0613/v1/完成文本-davinci-003、文本-davinci-002、文本-curie-001、文本-babbage-001、文本-ada-001/v1/编辑文本-davinci-edit-001，代码-davinci-edit-001/v1/音频/转录耳语-1/v1/音频/翻译耳语-1/v1/微调达芬奇、居里、巴贝奇、阿达/v1/嵌入文本嵌入-ada-002，文本搜索-ada-doc-001/v1/审核文本审核稳定，文本审核最新