> 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

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

[LLaDA](https://huggingface.co/GSAI-ML/LLaDA-8B-Base) is a diffusion language model that generates text through iterative masked-token denoising.

|                  |                                                      |
| ---------------- | ---------------------------------------------------- |
| **Task**         | Diffusion Language Modeling                          |
| **Architecture** | `LLaDAModelLM` with Hugging Face `trust_remote_code` |
| **Parameters**   | 8B                                                   |
| **HF Org**       | [GSAI-ML](https://huggingface.co/GSAI-ML)            |

## Example Model and Recipes

| Model                                                                   | Recipe                                                                                          |
| ----------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| [`GSAI-ML/LLaDA-8B-Base`](https://huggingface.co/GSAI-ML/LLaDA-8B-Base) | [Full SFT](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/llada_sft.yaml) |
| [`GSAI-ML/LLaDA-8B-Base`](https://huggingface.co/GSAI-ML/LLaDA-8B-Base) | [LoRA](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/llada_lora.yaml)    |

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

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