# Select Trainer

Select the appropriate trainer - which guides the model you select for training

<figure><img src="/files/gZIfkHO5PcTQ1gBK1x4j" alt=""><figcaption></figcaption></figure>

We offer three trainers to optimize your models:

<table data-view="cards"><thead><tr><th>Trainer</th><th>Definition</th><th>How it works</th><th>Best for</th><th data-hidden data-card-cover data-type="image">Cover image</th></tr></thead><tbody><tr><td><strong>SFT (Supervised fine-tuning)</strong></td><td>Foundational technique that trains your model on input-output pairs, teaching it to produce desired responses for specific inputs.</td><td>- Provide examples of correct responses to prompts to guide the model’s behavior.<br>- Often uses human-generated “ground truth” responses to show the model how it should respond.</td><td>- Classification<br>- Nuanced translation<br>- Generating content in a specific format<br>- Correcting instruction-following failures</td><td data-object-fit="contain"><a href="/files/xMC6luucfFVeqEgrdEUK">/files/xMC6luucfFVeqEgrdEUK</a></td></tr><tr><td><strong>DPO (Direct preference optimization)</strong></td><td>Trains models to prefer certain types of responses over others by learning from comparative feedback, without requiring a separate reward model.</td><td>- Provide both correct and incorrect example responses for a prompt.<br>- Indicate the correct response to help the model perform better.</td><td>- Summarizing text, focusing on the right things<br>- Generating chat messages with the right tone and style</td><td data-object-fit="contain"><a href="/files/rKJijCT5ZdlnOw66PfXf">/files/rKJijCT5ZdlnOw66PfXf</a></td></tr><tr><td><strong>Pre-training</strong></td><td>Initial training phase using large unlabeled data for language understanding.</td><td>- Exposes the model to vast amounts of text data to learn grammar, facts, reasoning patterns, and world knowledge.<br>- No labeled examples required.</td><td>- Building foundational language understanding<br>- Preparing models for downstream fine-tuning tasks</td><td data-object-fit="contain"><a href="/files/vpBNBXkaeQPxzoqjeEBH">/files/vpBNBXkaeQPxzoqjeEBH</a></td></tr></tbody></table>

<br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-docs.fptcloud.com/fpt-ai-studio/services/model-fine-tuning/tutorials/how-to-create-a-pipeline/select-trainer.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.