FineTunePreferenceRequestInput

The per-line training example of a fine-tuning input file for chat models using the dpo method.
{
    "input": {
        "messages": [
            {
                "content": "string",
                "role": "system",
                "name": "string"
            }
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "description": "string",
                    "name": "string",
                    "parameters": {},
                    "strict": false
                }
            }
        ],
        "parallel_tool_calls": true
    },
    "preferred_completion": [
        {
            "content": "string",
            "refusal": "string",
            "role": "assistant",
            "name": "string",
            "audio": {
                "id": "string"
            },
            "tool_calls": [
                {
                    "id": "string",
                    "type": "function",
                    "function": {
                        "name": "string",
                        "arguments": "string"
                    }
                }
            ],
            "function_call": {
                "arguments": "string",
                "name": "string"
            }
        }
    ],
    "non_preferred_completion": [
        {
            "content": "string",
            "refusal": "string",
            "role": "assistant",
            "name": "string",
            "audio": {
                "id": "string"
            },
            "tool_calls": [
                {
                    "id": "string",
                    "type": "function",
                    "function": {
                        "name": "string",
                        "arguments": "string"
                    }
                }
            ],
            "function_call": {
                "arguments": "string",
                "name": "string"
            }
        }
    ]
}