# Custom model development

> Custom model development - Custom model development accelerators that you can add to your experiment
> workflow.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-01T23:10:47.733994+00:00` (UTC).

## Primary page

- [Custom model development](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/index.html): Full documentation for this topic (HTML).

## Related documentation

- [Developer documentation](https://docs.datarobot.com/en/docs/api/index.html): Linked from this page.
- [Developer learning](https://docs.datarobot.com/en/docs/api/dev-learning/index.html): Linked from this page.
- [AI accelerators](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/index.html): Linked from this page.
- [Create and deploy a custom model](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/create-custom-model.html): Linked from this page.
- [Custom blueprints with Composable ML](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/custom-bp-nb.html): Linked from this page.
- [GraphSAGE custom transformer](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/custom-transform.html): Linked from this page.
- [Google Gemini integration](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/gemini-google.html): Linked from this page.
- [GIN financial fraud detection](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/graph-gin.html): Linked from this page.
- [Llama 2 on GCP](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/llama.html): Linked from this page.
- [LLM custom inference template](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/llm-template.html): Linked from this page.
- [Mistral 7B on GCP](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/mistral-7b.html): Linked from this page.
- [Reinforcement learning](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/reinforce-learn.html): Linked from this page.
- [Scoring Code microservice](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/sc-micro.html): Linked from this page.
- [Optimize custom model metrics with hyperparameter tuning](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/custom-model-dev/opt-custom-metric.html): Linked from this page.

## Documentation content

# Custom model development

| Topic | Description |
| --- | --- |
| Create and deploy a custom model | How to create, deploy, and monitor a custom inference model with DataRobot's Python client. You can use the Custom Model Workshop to upload a model artifact to create, test, and deploy custom inference models to DataRobot’s centralized deployment hub. |
| Custom blueprints with Composable ML | Customize models on the Leaderboard using the Blueprint Workshop. |
| GraphSAGE custom transformer | Convert a tabular dataset into a graph representation, train a GraphSAGE-based neural network, and package the solution as a DataRobot custom transformer. |
| Google Gemini integration | Implement a Streamlit application based on Google Gemini LLM and host it on the DataRobot platform with Vertex AI integration. |
| GIN financial fraud detection | Integrate a Graph Isomorphism Network (GIN) as a custom model task in DataRobot using DRUM. |
| Llama 2 on GCP | Host Llama 2 on Google Cloud Platform with cost comparisons, infrastructure details, and integration with DataRobot's custom model framework. |
| LLM custom inference template | The LLM custom inference model template enables you to deploy and accelerate your own LLM, along with "batteries-included" LLMs like Azure OpenAI, Google, and AWS. |
| Mistral 7B on GCP | Host Mistral 7B on Google Cloud Platform with infrastructure setup, cost considerations, and DataRobot integration for monitoring and deployment. |
| Reinforcement learning | Implement a model based on the Q-learning algorithm. |
| Scoring Code microservice | Follow a step-by-step procedure to embed Scoring Code in a microservice and prepare it as the Docker container for a deployment on customer infrastructure (it can be self- or hyperscaler-managed K8s). |
| Optimize custom model metrics with hyperparameter tuning | Improve DataRobot models using custom loss functions and advanced hyperparameter tuning. |