> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo-platform/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo-platform/_mcp/server.

# Fine-Tuning Tutorials

Use the tutorials in this section to gain a deeper understanding of how the NVIDIA NeMo Customizer microservice enables fine-tuning tasks.

Tutorials are organized by complexity and typically build on one another. The tutorials reference `NMP_BASE_URL`, which is the base URL of your NeMo Platform deployment. Refer to the [Setup guide](/documentation/get-started) for installation, setup, and platform URL guidance.

***

## Getting Started

Learn the fundamentals of how NeMo Customizer works with Model Entities and Adapters, and how to choose the right approach for your project.

<small>
  model-entities

   

  adapters

   

  training-types
</small>

## Dataset Preparation

Learn how to format datasets for different model types.

<small>
  datasets

   

  chat-models

   

  completion-models
</small>

## Customization Jobs

Learn how to perform supervised fine-tuning with LoRA adapters using custom data.

<small>
  nemo-customizer
</small>

Learn how to perform supervised fine-tuning using custom data by modifying the all training parameters.

<small>
  nemo-customizer
</small>

Learn how to compress a larger teacher model into a smaller student model using knowledge distillation.

<small>
  nemo-customizer

   

  knowledge-distillation
</small>

Learn how to fine-tune embedding models using LoRA merged training for improved question-answering and retrieval tasks.

<small>
  embedding-models

   

  lora-merged

   

  nemo-customizer
</small>

## Monitoring & Optimization

Learn how to check job metrics using MLflow or Weights & Biases.

<small>
  nemo-customizer

   

  mlflow

   

  wandb
</small>

Learn how to optimize the token-per-GPU throughput for a LoRA optimization job.

<small>
  nemo-customizer

   

  wandb

   

  sequence-packing
</small>