Quickstart

This guide walks you through training your first model on Adaptive Engine. You’ll create a project, deploy a base model, upload training data, run fine-tuning, and test the results. Train a customer service agent to respond like a poet.

Create a project

Projects organize your models, data, and training runs.

Deploy a model

Attach a model to deploy it for inference.

Upload a dataset

Datasets contain examples that teach your model how to respond.Download: fun-poet-completions.jsonl

Run fine-tuning

SFT (supervised fine-tuning) trains your model on labeled examples.

Test your model

Deploy and chat with your fine-tuned model.

Set ADAPTIVE_URL and ADAPTIVE_API_KEY environment variables before starting. See Authentication for details.

Create a project

Projects organize your models, data, and training runs.

pip install adaptive_sdk

import os
from adaptive_sdk import Adaptive

adaptive = Adaptive(
    base_url=os.environ["ADAPTIVE_URL"],
    api_key=os.environ["ADAPTIVE_API_KEY"],
)

adaptive.projects.create(key="quickstart-fun-poet")
adaptive.set_default_project("quickstart-fun-poet")

Deploy a model

Attach a model to deploy it for inference.

adaptive.models.attach(
    model="qwen-3-4b-instruct-2507",
    wait=True,
)

The model becomes available within a few minutes.

Upload a dataset

Datasets contain examples that teach your model how to respond.Download: fun-poet-completions.jsonl

adaptive.datasets.upload(
    file_path="fun-poet-completions.jsonl",
    dataset_key="fun-poet-completions",
)

Run fine-tuning

SFT (supervised fine-tuning) trains your model on labeled examples.

job = adaptive.jobs.run(
    recipe_key="sft",
    num_gpus=1,
    args={
        "model_to_train": "qwen-3-4b-instruct-2507",
        "output_model_key": "fun-poet-v1",
        "dataset": "fun-poet-completions",
        "epochs": 3,
        "samples_per_batch": 16,
        "tp": 1,
    },
)
print(f"Job started: {job.id}")

Training takes 15-30 minutes. Check progress in the UI under Runs.

Test your model

Deploy and chat with your fine-tuned model.

adaptive.models.attach(
    model="fun-poet-v1",
    wait=True,
)

response = adaptive.chat.create(
    model="fun-poet-v1",
    messages=[
        {"role": "user", "content": "I can't log into my account"}
    ],
)
print(response.choices[0].message.content)

The response should rhyme.

Next steps

Track metrics

Rate responses to build training data

Training recipes

SFT, RLHF, DPO, and other methods

Start

Core

Advanced

Deploy

Updates

Next steps

Track metrics

Training recipes

​Next steps

Track metrics

Training recipes

Next steps