Alibaba Cloud Model Studio：使用 API 或命令列進行模型調優

SFT 訓練集

SFT ChatML（Chat Markup Language）格式訓練資料，支援多輪對話和多種角色設定。

不支援OpenAI 的name、weight參數，所有的 assistant 輸出都會被訓練。

# 一行訓練資料（json 格式），展開後典型結構如下:
{"messages": [
  {"role": "system", "content": "系統輸入1"},
  {"role": "user", "content": "使用者輸入1"},
  {"role": "assistant", "content": "期望的模型輸出1"},
  {"role": "user", "content": "使用者輸入2"},
  {"role": "assistant", "content": "期望的模型輸出2"}
  ...
]}

system/user/assistant 區別請參見概述，訓練資料集範例：SFT-ChatML格式樣本.jsonl、SFT-ChatML格式樣本.xlsx（xls、xlsx 格式只支援單輪對話）。

單條訓練資料的所有 assistant 行都支援"loss_weight"參數，用於設定該行在訓練時的相對重要性。（設定範圍0.0 ~ 1.0，數值越大，重要性越高）

該參數屬於邀測參數，如需使用，請聯絡您的商務經理。

 {"role": "assistant", "content": "期望的模型輸出1", "loss_weight": 1.0},
 {"role": "assistant", "content": "期望的模型輸出2", "loss_weight": 0.5}

OpenAI 相容 - FIle 介面

import os
from pathlib import Path
from openai import OpenAI

client = OpenAI(
    # 若沒有配置環境變數，請用阿里雲百鍊API Key將下行替換為：api_key="sk-xxx",
    # 新加坡和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 以下為新加坡地區url，若使用北京地區的服務，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

# test.jsonl 是一個本地樣本檔案
file_object = client.files.create(file=Path("test.jsonl"), purpose="fine-tune")

print(file_object.model_dump_json())

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.files.*;

import java.nio.file.Path;
import java.nio.file.Paths;

public class Main {
    public static void main(String[] args) {
        // 建立用戶端，使用環境變數中的API密鑰
        OpenAIClient client = OpenAIOkHttpClient.builder()
                // 新加坡和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // 以下為新加坡地區url，若使用北京地區的服務，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1
                .baseUrl("https://dashscope-intl.aliyuncs.com/compatible-mode/v1")
                .build();
        // 設定檔案路徑,請根據實際需求修改路徑與檔案名稱
        Path filePath = Paths.get("src/main/java/org/example/test.txt");
        // 建立檔案上傳參數
        FileCreateParams params = FileCreateParams.builder()
                .file(filePath)
                .purpose(FilePurpose.of("fine-tune"))
                .build();

        // 上傳檔案
        FileObject fileObject = client.files().create(params);
        System.out.println(fileObject);
    }
}

# ======= 重要提示 =======
# 新加坡和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# 以下為新加坡地區url，若使用北京地區的服務，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1/files
# === 執行時請刪除該注釋 ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/files \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
--form 'file=@"test.jsonl"' \
--form 'purpose="fine-tune"'

HTTP

Windows CMD 請將${DASHSCOPE_API_KEY}替換為 %DASHSCOPE_API_KEY%，PowerShell 請替換為 $env:DASHSCOPE_API_KEY

curl --location "https://dashscope.aliyuncs.com/api/v1/fine-tunes" \
--header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
--header 'Content-Type: application/json' \
--data '{
    "model":"qwen3-8b",
    "training_datasets":[
        {"data_source_type":"file_id","file_id":"<替換為訓練資料集的file_id1>"},
        {"data_source_type":"oss_mount","mount_storage":{"region":"cn-beijing","bucket":"example_bucket","file_path":"dataset/data.jsonl"}}
    ],
    "validation_datasets":[
        {"data_source_type":"file_id","file_id":"<替換為測試資料集的file_id>"},
        {"data_source_type":"oss_mount","mount_storage":{"region":"cn-beijing","bucket":"example_bucket","file_path":"dataset/val.jsonl"}}
    ],
    "hyper_parameters":
    {
        "n_epochs": 3,
        "batch_size": 16,
        "max_length": 8192,
        "learning_rate": "1.6e-5",
        "lr_scheduler_type": "linear",
        "split": 0.9,
        "warmup_ratio": 0.05,
        "eval_steps": 50,
        "data_augmentation": true,
        "augmentation_ratio": "0.1,0.05,0.15",
        "augmentation_types": "dialogue_CN,general_purpose_CN,NLP",
        "save_strategy": "epoch",
        "save_total_limit": 10
    },
    "training_type":"sft"
}'

輸入參數

返回範例

{
    "request_id": "635f7047-003e-4be3-b1db-6f98e239f57b",
    "output":
    {
        "job_id": "ft-202511272033-8ae7",
        "job_name": "ft-202511272033-8ae7",
        "status": "PENDING",
        "finetuned_output": "qwen3-8b-ft-202511272033-8ae7",
        "model": "qwen3-8b",
        "base_model": "qwen3-8b",
        "training_file_ids": [],
        "validation_file_ids": [],
        "training_datasets": [
            {"data_source_type": "file_id", "file_id": "9e9ffdfa-c3bf-436e-9613-6f053c66aa6e"}
        ],
        "validation_datasets": [],
        "hyper_parameters":
        {
            "n_epochs": 3,
            "batch_size": 16,
            "max_length": 8192,
            "learning_rate": "1.6e-5",
            "lr_scheduler_type": "linear",
            "split": 0.9,
            "warmup_ratio": 0.05,
            "eval_steps": 50,
            "data_augmentation": true,
            "augmentation_ratio": "0.1,0.05,0.15",
            "augmentation_types": "dialogue_CN,general_purpose_CN,NLP",
            "save_strategy": "epoch",
            "save_total_limit": 10
        },
        "training_type": "sft",
        "create_time": "2025-11-27 20:33:15",
        "workspace_id": "llm-8v53etv3hwb8orx1",
        "user_identity": "1654290265984853",
        "modifier": "1654290265984853",
        "creator": "1654290265984853",
        "group": "llm",
        "max_output_cnt": 10
    }
}

HTTP

curl 'https://dashscope.aliyuncs.com/api/v1/fine-tunes/<job_id>' \
--header 'Authorization: Bearer '${DASHSCOPE_API_KEY} \
--header 'Content-Type: application/json'

輸入參數

返回成功範例

{
    "request_id": "d100cddb-ac85-4c82-bd5c-9b5421c5e94d",
    "output":
    {
        "job_id": "ft-202511272033-8ae7",
        "job_name": "ft-202511272033-8ae7",
        "status": "RUNNING",
        "finetuned_output": "qwen3-8b-ft-202511272033-8ae7",
        "model": "qwen3-8b",
        "base_model": "qwen3-8b",
        "training_file_ids": [],
        "validation_file_ids": [],
        "training_datasets": [
            {"data_source_type": "file_id", "file_id": "9e9ffdfa-c3bf-436e-9613-6f053c66aa6e"}
        ],
        "validation_datasets": [],
        "hyper_parameters":
        {
            "n_epochs": 3,
            "batch_size": 16,
            "max_length": 8192,
            "learning_rate": "1.6e-5",
            "lr_scheduler_type": "linear",
            "split": 0.9,
            "warmup_ratio": 0.05,
            "eval_steps": 50,
            "data_augmentation": true,
            "augmentation_ratio": "0.1,0.05,0.15",
            "augmentation_types": "dialogue_CN,general_purpose_CN,NLP",
            "save_strategy": "epoch",
            "save_total_limit": 10
        },
        "training_type": "sft",
        "create_time": "2025-11-27 20:33:15",
        "workspace_id": "llm-8v53etv3hwb8orx1",
        "user_identity": "1654290265984853",
        "modifier": "1654290265984853",
        "creator": "1654290265984853",
        "group": "llm",
        "max_output_cnt": 10
    }
}

HTTP

curl 'https://dashscope.aliyuncs.com/api/v1/fine-tunes/<job_id>/logs?offset=0&line=1000' \
--header 'Authorization: Bearer '${DASHSCOPE_API_KEY} \
--header 'Content-Type: application/json'

可通過 offset 和 line 兩個參數擷取特定行數區間的日誌。 Offset 用於設定日誌輸出開始的位置；line 用於設定日誌最多輸出多少行。

返回結果範例：

{
    "request_id":"1100d073-4673-47df-aed8-c35b3108e968",
    "output":{
        "total":57,
        "logs":[
            "{輸出調優日誌1}",
            "{輸出調優日誌2}",
            ...
            ...
            ...
        ]
    }
}