> This page is for version 0.7.0 · 26.10.
> For other versions, use one of these documentation indexes:
> - Nightly (default): https://docs.nvidia.com/nemo/automodel/nightly/llms.txt
> - Latest: https://docs.nvidia.com/nemo/automodel/latest/llms.txt
> - 0.7.0 · 26.10: https://docs.nvidia.com/nemo/automodel/v0.7/llms.txt
> - 0.5.0 · 26.06: https://docs.nvidia.com/nemo/automodel/v0.5/llms.txt
> - 0.4.0 · 26.04: https://docs.nvidia.com/nemo/automodel/v0.4/llms.txt

> 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.

# Llama-3.2-1B

> Use NeMo AutoModel to fine-tune Llama-3.2-1B for Embedding workflows with checked-in feature extraction recipes and documented distributed settings.

[Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) has a checked-in NeMo AutoModel recipe for feature extraction.
The Hugging Face configuration declares the `LlamaForCausalLM` architecture.

## Fine-Tune Llama-3.2-1B

Follow the [installation instructions](/nemo/automodel/v0.7/get-started/installation), then run the recipe from the repository root:

```bash
uv run automodel examples/retrieval/bi_encoder/llama3_2_1b.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/r0.7.0/examples/retrieval/bi_encoder/llama3_2_1b.yaml). |
| Prepare your environment              | Follow the [installation instructions](/nemo/automodel/v0.7/get-started/installation).                                                                   |

### Configuration

| Setting  | Configuration                |
| -------- | ---------------------------- |
| Hardware | -                            |
| Strategy | FSDP2; tp_size=1, cp_size=1  |
| Nodes    | 1                            |
| Features | Checkpointing (enabled=true) |
| Advanced | bfloat16                     |

## Model Reference

### Model Architecture

| Property     | Value              |
| ------------ | ------------------ |
| Task         | Feature extraction |
| Architecture | `LlamaForCausalLM` |

### Available Models

* [`meta-llama/Llama-3.2-1B`](https://huggingface.co/meta-llama/Llama-3.2-1B)

## Related Resources

* [Installation instructions](/nemo/automodel/v0.7/get-started/installation)