開放模型的監督式和蒸餾微調

import os
import time
import uuid
import vertexai

vertexai.init(project=PROJECT_ID, location=REGION)

from google.cloud import aiplatform
from vertexai.tuning import sft, SourceModel

pip install google-genai

import os
import time
import uuid

from google import genai
from google.genai import types
client = genai.Client(vertexai=True, project=PROJECT_ID, location=REGION)

{"prompt": "<prompt text>", "completion": "<ideal generated text>"}

{"messages": [
  {"content": "You are a chatbot that helps with scientific literature and generates state-of-the-art abstracts from articles.",
    "role": "system"},
  {"content": "Summarize the paper in one paragraph.",
    "role": "user"},
  {"content": " Here is a one paragraph summary of the paper:\n\nThe paper describes PaLM, ...",
    "role": "assistant"}
]}

{
"systemInstruction": {
  "parts": [{ "text": "You are a chatbot that helps with scientific literature and generates state-of-the-art abstracts from articles." }]},
"contents": [
  {"role": "user",
    "parts": [{ "text": "Summarize the paper in one paragraph." }]},
  {"role": "assistant",
    "parts": [{ "text": "Here is a one paragraph summary of the paper:\n\nThe paper describes PaLM, ..." }]}
]}

{"messages": [
  {"role": "user", "content": [
    {"type": "text", "text": "You are a chatbot that helps with scientific literature and generates state-of-the-art abstracts from articles."},
    {"type": "image_url", "image_url": {
      "url": "gs://your-gcs-bucket/your-image.jpeg",
      "detail": "low"}}]
  },
  {"role": "assistant", "content": [
    {"type": "text", "text": "Here is a one paragraph summary of the paper:\n\nThe paper describes PaLM, ..."}]
  },
  {"role": "user", "content": [
    {"type": "text", "text": "You are a chatbot that helps with scientific literature and generates state-of-the-art abstracts from articles."},
    {"type": "image_url", "image_url": {
      "url": "data:image/jpeg;base64,<base64 image>",
      "detail": "low"}}]
  },
  {"role": "assistant", "content": [
    {"type": "text", "text": "Here is a one paragraph summary of the paper:\n\nThe paper describes PaLM, ..."}]
  },
]}

{
"systemInstruction": {
  "parts": [{ "text": "You are a chatbot that helps with scientific literature and generates state-of-the-art abstracts from articles." }]},
"contents": [
  {"role": "user",
    "parts": [
      {"text": "You are a chatbot that helps with scientific literature and generates state-of-the-art abstracts from articles." },
      {"file_data": {
        "mime_type": "image/jpeg", "file_uri": "gs://your-gcs-bucket/your-image.jpeg"}}]
  },
  {"role": "assistant",
    "parts": [{ "text": "Here is a one paragraph summary of the paper:\n\nThe paper describes PaLM, ..." }]}
]}

sft_tuning_job = sft.train(
    source_model=SourceModel(
      base_model="meta/llama3_1@llama-3.1-8b",
      # Optional, folder that is either a custom model checkpoint or previously tuned model
      custom_base_model="gs://{STORAGE-URI}",
    ),
    tuning_mode="FULL", # FULL or PEFT_ADAPTER
    epochs=3,
    train_dataset="gs://{STORAGE-URI}", # JSONL file
    validation_dataset="gs://{STORAGE-URI}", # JSONL file
    output_uri="gs://{STORAGE-URI}",
)

tuning_job = client.tunings.tune(
    base_model="qwen/qwen3@qwen3-4b",
    training_dataset=types.TuningDataset(
        gcs_uri="gs://{STORAGE-URI}"
    ),
    config=types.CreateTuningJobConfig(
        method="DISTILLATION",
        base_teacher_model="qwen/qwen3-next-80b-a3b-thinking-maas",
        epoch_count=3,
        validation_dataset=types.TuningValidationDataset(
            gcs_uri="gs://{STORAGE-URI}"
        ),
        output_uri="gs://{STORAGE-URI}",
    ),
)

from vertexai.preview import model_garden

MODEL_ARTIFACTS_STORAGE_URI = "gs://{STORAGE-URI}/postprocess/node-0/checkpoints/final"

model = model_garden.CustomModel(
    gcs_uri=MODEL_ARTIFACTS_STORAGE_URI,
)

# deploy the model to an endpoint using GPUs. Cost will incur for the deployment
endpoint = model.deploy(
  machine_type="g2-standard-12",
  accelerator_type="NVIDIA_L4",
  accelerator_count=1,
)