Add files via upload

添加一处注释

注意:此处在原教程的基础上添加了一个示例,主要是因为"gpt-3.5-turbo"模型不能很好适应理解模板的意思,使用 "text-davinci-003" 或者"gpt-4-0613"可以很好的工作,因此在这里多加了示例提示让其更好的学习。
eg:
<< INPUT >>
"What is black body radiation?"
<< OUTPUT >>
```json
{{{{
    "destination": string \ name of the prompt to use or "DEFAULT"
    "next_inputs": string \ a potentially modified version of the original input
}}}}
```
This commit is contained in:
xuhu0115
2023-07-06 11:18:38 +08:00
committed by GitHub
parent 77bc8c89e2
commit 8eaf2ca54d

View File

@ -1222,6 +1222,25 @@
"这包括要完成的任务的说明以及输出应该采用的特定格式。"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "24f30c2c",
"metadata": {},
"source": [
"注意:此处在原教程的基础上添加了一个示例,主要是因为\"gpt-3.5-turbo\"模型不能很好适应理解模板的意思,使用 \"text-davinci-003\" 或者\"gpt-4-0613\"可以很好的工作,因此在这里多加了示例提示让其更好的学习。\n",
"eg:\n",
"<< INPUT >>\n",
"\"What is black body radiation?\"\n",
"<< OUTPUT >>\n",
"```json\n",
"{{{{\n",
" \"destination\": string \\ name of the prompt to use or \"DEFAULT\"\n",
" \"next_inputs\": string \\ a potentially modified version of the original input\n",
"}}}}\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 32,