# Specializing a pre-trained Model

HuggingFace and similar hubs for models with open trained weights are a great
way to get started, however, it is likely that these models will not perform
as well for your particular data.

In this section, we will focus on specializing pre-trained models with your
custom data. We will target AMD CPU and GPU.

Technologies covered: CPU, GPU.

## Requisites

```{card}
GPUs: {bdg-primary}`AMD Instinct™ Accelerators`, {bdg-primary}`AMD Radeon™ RX Graphics Cards` or {bdg-primary}`AMD Radeon™ PRO Graphics Cards`
```

[Setup environment](env/env.md)

## Examples

```{tableofcontents}
```

## Resources

- [Retrieval Augmented Generation (RAG) using LlamaIndex](https://rocm.blogs.amd.com/artificial-intelligence/rag-llamaindex/README.html)
- [How to enable RAG (Retrieval Augmented Generation) on an AMD Ryzen™ AI PC or Radeon Graphics Card](https://community.amd.com/t5/ai/how-to-enable-rag-retrieval-augmented-generation-on-an-amd-ryzen/ba-p/670670)
- [How to get an AI coding assistant on your AMD Ryzen™ AI PC or Radeon Graphics Card](https://community.amd.com/t5/ai/how-to-get-an-ai-coding-assistant-on-your-amd-ryzen-ai-pc-or/ba-p/670686)

If you would like to suggest a resource, email us aup@amd.com

----------
Copyright (C) 2025 Advanced Micro Devices, Inc. All rights reserved.

SPDX-License-Identifier: MIT