> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/QwenLM/Qwen3-VL/llms.txt
> Use this file to discover all available pages before exploring further.

# Training Overview

> Learn how to fine-tune Qwen3-VL models with the official training framework

## Introduction

The Qwen3-VL training framework provides a comprehensive solution for fine-tuning vision-language models. Built on top of the Hugging Face Trainer, it supports various training scenarios including single-image, multi-image, video understanding, and grounding tasks.

## Repository Structure

The training framework is organized into three main components:

### `train/`

Core training modules:

* `trainer.py`: Main trainer updated from Hugging Face Trainer
* `train_qwen.py`: Main file for training execution
* `argument.py`: Dataclasses for model, data and training arguments

### `data/`

Data processing utilities:

* `__init__.py`: Contains dataset configs
* `data_processor.py`: Data processing module for QwenVL models
* `rope2d.py`: Provides RoPE implementation

### `tools/`

Utility scripts:

* `process_bbox.ipynb`: Convert bounding boxes into QwenVL format for grounding data
* `pack_data.py`: Pack data into even length buckets for efficient training

## Requirements

The following package versions are recommended:

```txt theme={null}
torch==2.6.0
torchvision==0.21.0
transformers==4.57.0.dev0
deepspeed==0.17.1
flash_attn==2.7.4.post1
triton==3.2.0
accelerate==1.7.0
torchcodec==0.2
peft==0.17.1
```

## When to Fine-tune

Consider fine-tuning Qwen3-VL when:

* **Domain-specific tasks**: You need the model to excel at specific visual understanding tasks in your domain
* **Custom data format**: Your application requires understanding of specialized visual patterns or formats
* **Performance optimization**: Zero-shot performance doesn't meet your requirements
* **Grounding tasks**: You need precise object localization and bounding box prediction
* **Video understanding**: Your application involves temporal reasoning and video analysis
* **Multi-image reasoning**: Tasks require comparing or relating information across multiple images

## Training Workflow

The typical fine-tuning workflow consists of two main steps:

1. **Customize your dataset**: Download data and implement the dataset configuration
2. **Modify training scripts**: Configure training parameters and launch training

> [!NOTE]
>
> For images and video data combined training, set `tune_mm_vision=False` in your training configuration.

## Next Steps

> **[Dataset Preparation](https://mintlify.com/QwenLM/Qwen3-VL/fine-tuning/dataset-preparation.md)**
>
> Learn how to format your data for training

> **[Training Configuration](https://mintlify.com/QwenLM/Qwen3-VL/fine-tuning/training-configuration.md)**
>
> Configure datasets and sampling rates

> **[Training Script](https://mintlify.com/QwenLM/Qwen3-VL/fine-tuning/training-script.md)**
>
> Complete training script reference

> **[LoRA Training](https://mintlify.com/QwenLM/Qwen3-VL/fine-tuning/lora.md)**
>
> Parameter-efficient fine-tuning with LoRA


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.