Alibaba Cloud Model Studio:Penerapkan model menggunakan API atau CLI

Prasyarat

• Anda telah membaca Ikhtisar Penerapan Model dan memahami model yang didukung serta langkah-langkah penerapan dasar.

• Buat Kunci API dan ekspor Kunci API sebagai variabel lingkungan.

1. Terapkan model

Perintah berikut menggunakan model kustom hasil fine-tuning qwen3-8b-ft-202511132025-0260 untuk membuat layanan khusus bernama qwen3-8b-ft-202511132025-0260.

Untuk mendapatkan ID model kustom, buka halaman Konsol Model Studio - fine-tuning model. Klik Task Name dari model yang ingin Anda terapkan, lalu klik Outputs, kemudian klik nama model berwarna biru. Hal ini akan membuka halaman My Models, tempat Anda dapat menemukan Model ID pada bagian informasi dasar.

Gunakan Model ID sebagai nilai parameter input model_name untuk menerapkan model melalui API.

curl "https://dashscope-intl.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "name": "my_qwen_flash",
    "model_name": "qwen-flash-2025-07-28",
    "plan": "ptu",
    "ptu_capacity": {
        "input_tpm": 10000,
	"output_tpm": 1000
    }
}'

curl "https://dashscope-intl.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "name": "my_qwen_plus",
    "model_name": "qwen-plus-2025-12-01",
    "plan": "mu",
    "deploy_spec": "MU1",
    "enable_thinking": true,
    "capacity": 4,
    "max_context_length": 10000,
    "rpm_limit": 500,
    "tpm_limit": 1000
}'

curl "https://dashscope-intl.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "qwen3-8b-ft-202511132025-0260",
    "plan": "lora",
    "capacity": 1,
    "name": "qwen3-8b-ft"
}'

Jika berhasil, perintah tersebut mengembalikan respons berikut (menggunakan contoh penerapan LoRA):

{
    "request_id": "83b173ab-2b2f-41aa-8c57-b173e8be934e",
    "output":
    {
        "deployed_model": "qwen3-8b-ft-202511132025-0260",
        "gmt_create": "2025-11-20T20:06:46.405",
        "gmt_modified": "2025-11-20T20:06:46.405",
        "status": "PENDING",
        "model_name": "qwen3-8b-ft-202511132025-0260",
        "base_model": "qwen3-8b",
        "workspace_id": "llm-8v*****",
        "charge_type": "post_paid",
        "creator": "16542*****",
        "modifier": "16542*****",
        "plan": "***"
    }
}

Di mana deployed_model adalah ID unik layanan khusus tersebut.

2. Kueri status layanan

Jalankan perintah berikut untuk mengkueri detail layanan khusus tertentu:

curl "https://dashscope-intl.aliyuncs.com/api/v1/deployments/qwen3-8b-ft-202511132025-0260" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header 'Content-Type: application/json' 

Jika berhasil, perintah tersebut mengembalikan respons berikut:

{
    "request_id": "ca36952d-9136-426e-ab08-68a97ad72719",
    "output":
    {
        "deployed_model": "qwen3-8b-ft-202511132025-0260",
        "gmt_create": "2025-11-20T20:32:08",
        "gmt_modified": "2025-11-20T20:42:25",
        "status": "RUNNING",
        "model_name": "qwen3-8b-ft-202511132025-0260",
        "base_model": "qwen3-8b",
        "base_capacity": 2,
        "capacity": 2,
        "ready_capacity": 2,
        "workspace_id": "llm-8v53etv3hwb8orx1",
        "charge_type": "post_paid",
        "creator": "1654290265984853",
        "modifier": "1654290265984853",
        "plan": "mu",
        "model_unit_spec": "MU1"
    }
}

Ketika status layanan adalah RUNNING, penerapan layanan telah selesai.

3. Kirim permintaan inferensi

Gunakan SDK untuk mengirim permintaan ke layanan khusus:

from dashscope import Generation
from http import HTTPStatus
import os
response = Generation.call(
    model='qwen3-8b',
    prompt='Who are you?',
    enable_thinking=False,
    api_key=os.getenv('DASHSCOPE_API_KEY'),
)
if response.status_code == HTTPStatus.OK:
    print(response.output)
    print(response.usage)
else:
    print(response.code)
    print(response.message)

Eksekusi yang berhasil mengembalikan respons berikut:

{"text": "I am Qwen, a large language model developed by Alibaba Cloud. I am designed to generate various types of text, such as articles, stories, and poems, and to engage in conversations, answer questions, provide information, and offer help in different scenarios. I'm happy to serve you! If you have any questions or need assistance, please feel free to let me know.", "finish_reason": "stop", "choices": null}
{"input_tokens": 11, "output_tokens": 63, "total_tokens": 74}

4. Hapus layanan khusus

Jika Anda tidak lagi memerlukan layanan khusus, Anda dapat menghapusnya menggunakan perintah berikut:

curl --request DELETE 'https://dashscope-intl.aliyuncs.com/api/v1/deployments/qwen3-8b-ft-202511132025-0260' \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header 'Content-Type: application/json' 

Jika berhasil, perintah tersebut mengembalikan respons berikut:

{
    "request_id": "8f726017-6042-420e-a465-0d366a3aba59",
    "output":
    {
        "deployed_model": "qwen3-8b-ft-202511132025-0260",
        "gmt_create": "2025-11-20T20:32:08",
        "gmt_modified": "2025-11-27T16:35:31.591",
        "status": "DELETING",
        "model_name": "qwen3-8b-ft-202511132025-0260",
        "base_model": "qwen3-8b",
        "base_capacity": 2,
        "capacity": 2,
        "ready_capacity": 2,
        "workspace_id": "llm-8v53etv3hwb8orx1",
        "charge_type": "post_paid",
        "creator": "1654290265984853",
        "modifier": "1654290265984853",
        "plan": "mu",
        "model_unit_spec": "MU1"
    }
}

Setelah menghapus layanan, Anda tidak dapat lagi mengkueri statusnya menggunakan metode yang dijelaskan di 2. Kueri status layanan.

Referensi API

Untuk detail panggilan API, lihat Detail API.