> 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.

# BAGEL-7B-MoT

> Use BAGEL-7B-MoT with NeMo AutoModel for multimodal pretraining, with documented checkpoints, runnable recipes, setup guidance, and model reference details.

[BAGEL-7B-MoT](https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT) is a unified multimodal model from ByteDance Seed. It combines a Qwen2 language backbone, a SigLIP-NaViT vision encoder, and mixture-of-transformations layers for mixed understanding and visual-generation training.

Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation).

## Pretrain BAGEL-7B-MoT

From the repository root, run:

```bash
uv run automodel --nproc-per-node=8 examples/multimodal_pretrain/bagel/bagel_pretrain.yaml
```

## Choose a Workflow

| Goal                                                      | Start Here                                                                                                                                                                          |
| --------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Joint text-understanding and image-generation pretraining | Use [bagel\_pretrain.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/multimodal_pretrain/bagel/bagel_pretrain.yaml). Dataset: BAGEL-style packed multimodal data. |
| Joint understanding + generation fine-tuning              | Use [bagel\_sft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/multimodal_finetune/bagel/bagel_sft.yaml). Dataset: BAGEL-style packed multimodal data.           |

## Model Reference

### Model Architecture

| Property                  | Value                                                        |
| ------------------------- | ------------------------------------------------------------ |
| Task                      | Multimodal Input/Output                                      |
| Architecture              | `BagelForUnifiedMultimodal`, `BagelForConditionalGeneration` |
| Parameters                | 14B (two 7B towers)                                          |
| Hugging Face Organization | [ByteDance-Seed](https://huggingface.co/ByteDance-Seed)      |

### Available Models

| Model        | HF ID                                                                               |
| ------------ | ----------------------------------------------------------------------------------- |
| BAGEL-7B-MoT | [`ByteDance-Seed/BAGEL-7B-MoT`](https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT) |

## Related Resources

* [Pretraining Guide](/recipes-e2e-examples/pretraining)