> 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.

# Laguna-XS-2.1

> Use NeMo AutoModel to fine-tune Laguna-XS-2.1 for LLM workflows with checked-in text generation recipes and documented distributed settings.

[Laguna-XS-2.1](https://huggingface.co/poolside/Laguna-XS-2.1) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `LagunaForCausalLM` architecture.

## Fine-Tune Laguna-XS-2.1

Follow the [installation instructions](/get-started/installation), then run the recipe from the repository root:

```bash
automodel examples/llm_finetune/laguna/laguna_xs_2p1_hellaswag_ep8.yaml --nproc-per-node 8
```

## 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/llm_finetune/laguna/laguna_xs_2p1_hellaswag_ep8.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, ep\_size=8                                                     |
| Nodes    | 1                                                                                                         |
| Features | Activation checkpointing (activation\_checkpointing=true), Packed sequences (packed\_sequence\_size=1024) |
| Advanced | bfloat16, attention=sdpa, linear=torch, experts=torch\_mm, dispatcher=torch                               |

## Model Reference

### Model Architecture

| Property     | Value               |
| ------------ | ------------------- |
| Task         | Text generation     |
| Architecture | `LagunaForCausalLM` |

### Available Models

* [`poolside/Laguna-XS-2.1`](https://huggingface.co/poolside/Laguna-XS-2.1)

## Related Resources

* [LLM fine-tuning guide](/recipes-e2e-examples/sft-peft)