Fine-tuning data upload rules

​

Overview

​

Training method and element support matrix

• SFT, local upload, log backflow, API upload, and multimodal data formats are supported in all regions.
• DPO, CPT, OSS import, and cloud storage mount are only supported in the Beijing region.

​

Text generation - SFT format

• Supports three roles: system, user, and assistant. The content field is a string (for the content array structure in multimodal scenarios, see the corresponding multimodal format chapter).
• Maximum single file size is 200 MB.
• A dataset can mix rows of different formats — each record independently selects a format, no need to unify into a single format.
• Available formats: standard ChatML, thinking, function calling, and function calling combined with thinking (see the sample tabbed pages below).

{
  "messages": [
    {"role": "system", "content": "System input 1"},
    {"role": "user", "content": "User input 1"},
    {"role": "assistant", "content": "Expected model output 1"},
    {"role": "user", "content": "User input 2"},
    {"role": "assistant", "content": "Expected model output 2"}
  ]
}

{"role": "assistant", "content": "Expected model output", "loss_weight": "1.0"}

{
  "messages": [
    {"role": "system", "content": "System input 1"},
    {"role": "user", "content": "User input 1"},
    {"role": "assistant", "content": "Model output 1"},
    {"role": "user", "content": "User input 2"},
    {"role": "assistant", "content": "<think>\nExpected thinking content 2\n</think>\n\nExpected output 2"}
  ]
}

​

Thinking tag rules

• It can only be placed in the last assistant output; intermediate assistant outputs must not include thinking tags.
• The line breaks before and after the thinking tag must be preserved.
• If a training sample is configured so that the model does not output thinking tags, it is not recommended to re-enable the thinking mode when calling the model after training.

​

Evaluation set format

• File format is xlsx; the column structure can be found in the template downloaded from the console.
• Ingestion methods: local upload and log replay; Object Storage Service (OSS) import and cloud storage mounting are not supported.
• Only draft versions support online editing (Prompt/Completion); published versions cannot be edited.

{"prompt": "Who painted the human body during the Renaissance?", "completion": "The Renaissance was a revival movement of art, culture, and scholarship, during which many artists painted the human body."}
{"prompt": "Why does the Sun emit light and heat?", "completion": "The Sun generates tremendous energy from the fusion of hydrogen nuclei under high temperature and pressure. This fusion reaction releases large amounts of light and heat."}
{"prompt": "Why is the sky blue?", "completion": "When sunlight reaches the Earth's atmosphere, the shorter-wavelength blue light is scattered by gas molecules in the atmosphere, forming the blue sky we see."}

• Supported log range is within the last 30 days.
• Maximum of 100,000 records per import.
• You must authorize the service-linked role and specify the API Key and model filter conditions.
• The training set is only available for SFT text generation scenarios (the text generation evaluation set is also supported).

​

Text generation - DPO format

{
  "messages": [
    {"role": "system", "content": "System input"},
    {"role": "user", "content": "User input 1"},
    {"role": "assistant", "content": "Model output 1"},
    {"role": "user", "content": "User input 2"},
    {"role": "assistant", "content": "Model output 2"},
    {"role": "user", "content": "User input 3"}
  ],
  "chosen": {"role": "assistant", "content": "Preferred expected model output 3"},
  "rejected": {"role": "assistant", "content": "Rejected expected model output 3"}
}

{
  "messages": [
    {"role": "system", "content": "System input"},
    {"role": "user", "content": "User input 1"},
    {"role": "assistant", "content": "Model output 1"},
    {"role": "user", "content": "User input 2"}
  ],
  "chosen": {"role": "assistant", "content": "<think>\nExpected thinking content\n</think>\n\nExpected model output"},
  "rejected": {"role": "assistant", "content": "Rejected expected model output 2"}
}

​

Text generation - CPT format

• A minimum of 50 million Tokens is recommended, and the single file size limit is 300 MB.
• Draft status and data inheritance are not supported; each new version requires creating new data and publishing immediately.

{
  "text": "Text content"
}

​

Visual understanding-SFT format

{
  "messages": [
    {"role": "system", "content": [{"text": "System input 1"}]},
    {"role": "user", "content": [{"text": "User input 1"}]},
    {"role": "assistant", "content": [{"text": "Expected model output 1"}]},
    {"role": "user", "content": [{"text": "User input 2"}]},
    {"role": "assistant", "content": [{"text": "Expected model output 2"}]}
  ]
}

{
  "messages": [
    {"role": "system", "content": [{"text": "System input 1"}]},
    {"role": "user", "content": [{"text": "User input 1"}]},
    {"role": "assistant", "content": [{"text": "Model output 1"}]},
    {"role": "user", "content": [{"text": "User input 2"}]},
    {"role": "assistant", "content": [{"text": "<think>\nExpected thinking content 2\n</think>\n\nExpected output 2"}]}
  ]
}

{
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Query real-time weather for a specified city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {"type": "string", "description": "City name, e.g.: Beijing"}
          },
          "required": ["city"]
        }
      }
    }
  ],
  "messages": [
    {"role": "user", "content": [{"text": "Help me check the weather in Beijing"}]},
    {
      "role": "assistant",
      "content": [{"text": "OK, I will help you query the weather in Beijing."}],
      "tool_calls": [
        {
          "id": "call_3a11c1ba883b41b6a4e0cb",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"city\": \"Beijing\"}"
          }
        }
      ]
    },
    {"role": "tool", "tool_call_id": "call_3a11c1ba883b41b6a4e0cb", "content": [{"text": "{\"city\": \"Beijing\", \"weather\": \"Sunny\", \"temperature\": \"25℃\"}"}]},
    {"role": "assistant", "content": [{"text": "Beijing is sunny today, with a temperature of 25°C, suitable for going out."}]}
  ]
}

{
  "messages": [
    {"role": "system", "content": [{"text": "System input"}]},
    {
      "role": "user",
      "content": [
        {"text": "User input 1"},
        {"image": "image_file1.jpg", "resized_width": 200, "resized_height": 200}
      ]
    },
    {"role": "assistant", "content": [{"text": "Expected model output 1"}]}
  ]
}

{
  "messages": [
    {"role": "system", "content": [{"text": "System input"}]},
    {
      "role": "user",
      "content": [
        {"text": "User input 1"},
        {"video": "video_file1.mp4", "fps": 3.0, "resized_width": 200, "resized_height": 200, "video_start": 0.0, "video_end": 3.0}
      ]
    },
    {"role": "assistant", "content": [{"text": "Expected model output 1"}]}
  ]
}

{
  "messages": [
    {"role": "system", "content": [{"text": "System input"}]},
    {
      "role": "user",
      "content": [
        {"text": "User input 2"},
        {"video": ["0.jpg", "1.jpg", "2.jpg", "3.jpg"], "sample_fps": 5.0, "resized_width": 200, "resized_height": 200}
      ]
    },
    {"role": "assistant", "content": [{"text": "Expected model output 2"}]}
  ]
}

​

Tool field description

• tools: tool definition array; each item contains type:"function" and function{name, description, parameters}; parameters is a JSON Schema (containing type/properties/required).
• messages: multi-turn dialogue array; roles include user, assistant, and tool.
• content: multimodal content array; can contain image, text, video, and other items (consistent with the multimodal understanding format).
• assistant.tool_calls: tool call array generated by the model; contains id, type:"function", function{name, arguments}; arguments is a JSON string.
• role:"tool": tool return; tool_call_id must correspond one-to-one with the corresponding tool_calls[].id; content contains the tool return result.

• Invite-only parameter; value range 0.0 to 1.0; the larger the value, the higher the relative importance of this row during training.
• For SFT thinking models, only the last assistant row supports loss_weight.

​

Thinking tag rules

• It must be placed only in the last assistant output; intermediate assistant outputs do not add thinking tags.
• The newlines before and after the thinking tags must be preserved.
• If the training samples set the model not to output thinking tags, after training is complete it is not recommended to enable the thinking mode for calls.

​

Multimodal zip package packaging rules

• The zip package supports up to 2 GB.
• The allowed character set for folder and file names inside the package is ASCII letters (a-z, A-Z), digits (0-9), underscores (_), and hyphens (-).
• The training text data file is fixed as data.jsonl and must be located in the root directory of the zip package — ensure that after extraction, opening the zip file directly shows data.jsonl, with no additional outer folder wrapping.

# Single-layer directory (recommended)
Trainingdata_vl.zip
  |--- data.jsonl        # Must be in the root directory, no outer folder wrapping
  |--- image1.png
  |--- video1.mp4

# Declare filename inside data.jsonl (not path)
# Correct: image1.jpg
# Wrong: jpg_folder/image1.jpg

​

File size and quantity limits

​

API upload quota

• Specify the data.jsonl root directory manifest path via MountStorage's file_path; zip archives are not supported.
• When selecting cloud storage mount as the storage location, immediate publish is enforced; draft status is not supported.
• Before mounting, you must authorize the Bailian service to access OSS data.

• Single file exceeding 300 MB: upload via cloud storage mount or the multi-modal ZIP 2 GB channel.
• Total quota exceeded: delete historical files to free up space.
• Imported data automatically enables OSS server-side encryption (SSE-OSS, AES256).

​

Upload validation and common errors

• Publish and delete operations are both irreversible; published versions cannot be edited again, and only draft versions can be deleted or edited online.
• Dataset type (training set/evaluation set) cannot be changed or interchanged after creation; selecting the wrong one requires creating a new dataset and re-importing all data.
• Switching dataset type, training scenario, or training method clears the uploaded files and resets the storage location and import method.