> 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.

# LLaDA 2.1

> Supported LLaDA 2.1 checkpoint and NeMo AutoModel diffusion-language recipes.

[LLaDA 2.1](https://huggingface.co/inclusionAI/LLaDA2.1-mini) is a mixture-of-experts diffusion language model supported through its Hugging Face remote-code implementation.

|                  |                                                          |
| ---------------- | -------------------------------------------------------- |
| **Task**         | Diffusion Language Modeling (MoE)                        |
| **Architecture** | `LLaDA2MoeModelLM` with Hugging Face `trust_remote_code` |
| **HF Org**       | [inclusionAI](https://huggingface.co/inclusionAI)        |

## Example Model and Recipes

| Model                                                                           | Recipe                                                                                           |
| ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
| [`inclusionAI/LLaDA2.1-mini`](https://huggingface.co/inclusionAI/LLaDA2.1-mini) | [Full SFT](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/llada2_sft.yaml) |
| [`inclusionAI/LLaDA2.1-mini`](https://huggingface.co/inclusionAI/LLaDA2.1-mini) | [LoRA](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/llada2_lora.yaml)    |

```bash
uv run automodel --nproc-per-node=8 examples/dllm_sft/llada2_sft.yaml
```

See the [dLLM Fine-Tuning Guide](/recipes-e2e-examples/dllm-fine-tuning).