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

# Qwen2.5-Omni-7B

> Use NeMo AutoModel to fine-tune Qwen2.5-Omni-7B for Omni workflows with checked-in any to any recipes and documented distributed settings.

[Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B) has a checked-in NeMo AutoModel recipe for any to any.
The Hugging Face configuration declares the `Qwen2_5OmniModel` architecture.

## Fine-Tune Qwen2.5-Omni-7B

Follow the [installation instructions](/get-started/installation), then review the checked-in recipe and
its declared topology below before choosing a local or cluster launcher.

## Choose a Workflow

| Goal                                  | Start Here                                                                                                                                   |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Run the primary recipe for this model | Use the [recipe configuration](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/audio_finetune/qwen2_5_omni_asr/ami_sft_7b.yaml). |
| Prepare your environment              | Follow the [installation instructions](/get-started/installation).                                                                           |

### Configuration

| Setting  | Configuration                                                                                               |
| -------- | ----------------------------------------------------------------------------------------------------------- |
| Hardware | -                                                                                                           |
| Strategy | FSDP2; tp\_size=1, pp\_size=1, cp\_size=1                                                                   |
| Nodes    | -                                                                                                           |
| Features | Checkpointing (enabled=true), Activation checkpointing (activation\_checkpointing=true), Transformer Engine |
| Advanced | attention=sdpa, linear=te                                                                                   |

## Model Reference

### Model Architecture

| Property     | Value              |
| ------------ | ------------------ |
| Task         | Any to any         |
| Architecture | `Qwen2_5OmniModel` |

### Available Models

* [`Qwen/Qwen2.5-Omni-7B`](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)

## Related Resources

* [Multimodal fine-tuning guide](/recipes-e2e-examples/gemma-3-3n)