# How to fine-tune LLMs with Helicone and OpenPipe

> Learn how to fine-tune large language models with Helicone and OpenPipe to optimize performance for specific tasks.

<Steps>
  <Step title="Add the OpenPipe Integration">
    Navigate to `Settings` -> `Connections` in your Helicone dashboard and configure the OpenPipe integration.

    <Frame>
      <img
        src="/images/use-cases/fine-tune/openpipe-integration.webp"
        alt="Configure OpenPipe Integration"
      />
    </Frame>

    This integration allows you to manage your fine-tuning datasets and jobs seamlessly within Helicone.

  </Step>

  <Step title="Create a Dataset for Fine-Tuning">
    Your dataset doesn't need to be enormous to be effective. In fact, smaller, high-quality datasets often yield better results.

    - **Recommendation**: Start with 50-200 examples that are representative of the tasks you want the model to perform.

<Frame>
  <img
    src="/images/use-cases/fine-tune/dataset.webp"
    alt="Create a new dataset"
  />
</Frame>

    Ensure your dataset includes clear input-output pairs to guide the model during fine-tuning.

  </Step>

  <Step title="Evaluate and Refine Your Dataset">
    Within Helicone, you can evaluate your dataset to identify any issues or areas for improvement.

    - **Review Samples**: Check for consistency and clarity in your examples.
    - **Modify as Needed**: Make adjustments to ensure the dataset aligns closely with your desired outcomes.

    <Frame>
      <img
        src="/images/use-cases/fine-tune/openpipe-button.webp"
        alt="Evaluate your dataset"
      />
    </Frame>

    Regular evaluation helps in creating a robust fine-tuning dataset that enhances model performance.

  </Step>

  <Step title="Configure Your Fine-Tuning Job">
    Set up your fine-tuning job by specifying parameters such as:

    - **Model Selection**: Choose the base model you wish to fine-tune.
    - **Training Settings**: Adjust hyperparameters like learning rate, epochs, and batch size.
    - **Validation Metrics**: Define how you'll measure the model's performance during training.

    <Frame>
      <img
        src="/images/use-cases/fine-tune/fine-tune-config.webp"
        alt="Configure your fine-tuning job"
        width="300"
      />
    </Frame>

    After configuring, initiate the fine-tuning process. Helicone and OpenPipe handle the heavy lifting, providing you with progress updates.

  </Step>

  <Step title="Deploy and Monitor Your Fine-Tuned Model">
    Once fine-tuning is complete:

    - **Deployment**: Integrate the fine-tuned model into your application via Helicone's API endpoints.
    - **Monitoring**: Use Helicone's observability tools to track performance, usage, and any anomalies.

  </Step>
</Steps>

## Additional Fine-Tuning Resources

For more information on fine-tuning, check out these resources:

- [Fine-Tuning Best Practices: Training Data](https://openpipe.ai/blog/fine-tuning-best-practices-series-introduction-and-chapter-1-training-data)
- [Fine-Tuning Best Practices: Models](https://openpipe.ai/blog/fine-tuning-best-practices-chapter-2-models)
- [How to use OpenAI fine-tuning API](/faq/openai-fine-tuning-api)
- [Understanding fine-tuning duration](/faq/llm-fine-tuning-time)
- [Comparing RAG and fine-tuning approaches](/faq/rag-vs-fine-tuning)