Intro

OpenAI Platform

When to use

不建议直接用 fine-tuning，建议

• first, try prompt engineering
• then, try prompt chaining(breaking complex tasks into multiple prompts)
• then, function calling
• at last, fine-tuning

试用场景

Some common use cases where fine-tuning can improve results:

• Setting the style, tone, format, or other qualitative aspects
• Improving reliability at producing a desired output
• Correcting failures to follow complex prompts
• Handling many edge cases in specific ways
• Performing a new skill or task that’s hard to articulate in a prompt

One high-level way to think about these cases is when it’s easier to "show, not tell".

• 语气、格式、质量相关
• 需要可靠地输出特定内容的
• 边界 case
• 不好用 prompt 说明的（easier to show than tell）

Pricing

Best Practise