> 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.

# T5

> Supported T5 checkpoints and NeMo AutoModel recipes.

[T5](https://huggingface.co/google-t5/t5-small) is Google's encoder-decoder text-to-text transformer family.

|                  |                                               |
| ---------------- | --------------------------------------------- |
| **Task**         | Text-to-Text Generation                       |
| **Architecture** | `T5ForConditionalGeneration`                  |
| **HF Org**       | [google-t5](https://huggingface.co/google-t5) |

## Example Model and Recipe

| Model                                                             | Recipe                                                                                                               |
| ----------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
| [`google-t5/t5-small`](https://huggingface.co/google-t5/t5-small) | [SQuAD fine-tuning](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/t5/t5_small_squad.yaml) |

## Run the Recipe

```bash
uv run automodel --nproc-per-node=8 examples/llm_finetune/t5/t5_small_squad.yaml
```

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