关于多Agent进行sft数据构建格式

[llm-zoo]

Reminder

• I have read the README and searched the existing issues.

System Info

transformers>=4.41.2,<=4.43.4
datasets>=2.16.0,<=2.20.0
accelerate>=0.30.1,<=0.32.0

Reproduction

llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml

Expected behavior

提供的用例格式如下：
[
{
"conversations": [
{
"from": "human",
"value": "人类指令"
},
{
"from": "function_call",
"value": "工具参数"
},
{
"from": "observation",
"value": "工具结果"
},
{
"from": "gpt",
"value": "模型回答"
}
],
"system": "系统提示词（选填）",
"tools": "工具描述（选填）"
}
]
我想构建一份设置多个agent分步处理得到最终结果并去微调qwen2-7b，但是我看关于sharegpt的格式要求，function_call，gpt必须设置在偶数位置，如使用以下格式是否正确？
[
{
"conversations": [
{
"from": "human",
"value": "人类指令"
},
{
"from": "function_call",
"value": "工具参数1"
},
{
"from": "observation",
"value": "工具结果1"
},
{
"from": "function_call",
"value": "工具参数2"
},
{
"from": "observation",
"value": "工具结果2"
},
{
"from": "gpt",
"value": "模型回答"
}
],
"system": "系统提示词（选填）",
"tools": "工具描述（选填）"
}
]

Others

No response

[Imbernoulli]

“提供的用例格式”是在哪里？

[xjtupy]

请问这个问题解决了嘛，我现在也有这么一个任务，拆分到多个agent去执行