> 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.

# gemma-7b

> Use gemma-7b with NeMo AutoModel for text generation, with supported architecture details, canonical checkpoints, and recipe references.

[Gemma 1](https://huggingface.co/google/gemma-7b) is the first generation of Google's open-weight Gemma language models.

## Fine-Tune gemma-7b

From the repository root, run:

```bash
uv run automodel --nproc-per-node=8 examples/llm_finetune/gemma/gemma_7b_squad.yaml
```

## Model Reference

### Model Architecture

| Property         | Value                                   |
| ---------------- | --------------------------------------- |
| **Task**         | Text Generation                         |
| **Architecture** | `GemmaForCausalLM`                      |
| **Parameters**   | 2B, 7B                                  |
| **HF Org**       | [google](https://huggingface.co/google) |

## Example Models and Recipes

| Model                                                       | Recipe                                                                                                          |
| ----------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
| [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) | [Full SFT](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/gemma/gemma_7b_squad.yaml)  |
| [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) | [LoRA](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/gemma/gemma_7b_squad_peft.yaml) |

See the [Installation Guide](/get-started/installation) and [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft).