> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Fine-tuning Quick Start

> Train your first specialized model from a ready dataset.

This quick start shows you how to train a task-specific model from a ready dataset in Studio and use the deployed artifact for evaluation and routing.

<Note>
  Before you begin, create a dataset with training entries. If you generated better targets with relabeling, wait for that relabel run to complete.
</Note>

<Steps>
  <Step title="Open Tuned Models">
    From the project, open **Tuned Models** and select **Fine Tune**.
  </Step>

  <Step title="Choose the training data">
    Select a ready dataset, then choose the original outputs or a completed relabel run as the targets the model should learn.
  </Step>

  <Step title="Select a base model">
    Choose one of the [supported training models](/model-distillation/supported-models). When compute is available, train more than one candidate instead of assuming the largest model will perform best.
  </Step>

  <Step title="Keep or customize the defaults">
    The fine-tune name is optional. For the first run, leave the training configuration automatic. To configure the run, expand the customization options. You can cap the training examples, set the batch size and epochs, and specify a peak learning rate or a full learning-rate schedule. You can also choose which assistant turns to train on or pass experimental W\&B Serverless Training options. See [Training parameters](/model-distillation/studio/fine-tuning#training-parameters) for details.
  </Step>

  <Step title="Start training">
    Select **Start training**. The model moves through **Queued** and **Training**, and Studio reports progress from 0 to 100%.
  </Step>

  <Step title="Use the deployed artifact">
    When the status becomes **Deployed**, the exact W\&B artifact appears in Studio and becomes available for evaluations and routing through `wandb-inference`.
  </Step>
</Steps>

Next, [evaluate the fine-tune](/model-distillation/studio/evaluations-quickstart) on held-out validation rows before sending production traffic to it.

<Accordion title="API: Start training (POST /tasks/{alias}/finetunes)">
  Omit `model_config` to use the automatic training configuration:

  ```bash theme={"system"}
  curl --request POST \
    --url "https://distillation.training.wandb.ai/v1/tasks/ticket-classifier/finetunes" \
    --header "Authorization: Bearer $WANDB_API_KEY" \
    --header "Wandb-Entity: your-team" \
    --header "Content-Type: application/json" \
    --data "{
      \"dataset_id\": \"$DATASET_ID\",
      \"model_name\": \"ticket-classifier-qwen\",
      \"base_model\": \"Qwen/Qwen3.6-27B\"
    }"
  ```

  Poll the returned fine-tune until it is `deployed` or `failed`. See [Create a fine-tune](/model-distillation/reference/management/fine-tunes/create-a-fine-tune).
</Accordion>