> 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-3.1-8B

> Use NeMo AutoModel to fine-tune Llama-3.1-8B for LLM workflows with checked-in text generation recipes and documented distributed settings.

[Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `LlamaForCausalLM` architecture.

## Fine-Tune Llama-3.1-8B

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

```bash
automodel examples/llm_finetune/llama3_1/llama3_1_8b_squad_qlora.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/llama3_1/llama3_1_8b_squad_qlora.yaml). |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_benchmark/llama3_1/llama3_1_8b_peft_benchmark.yaml). |

### Configuration

| Setting  | Configuration                 |
| -------- | ----------------------------- |
| Hardware | -                             |
| Strategy | FSDP2; tp\_size=1, cp\_size=1 |
| Nodes    | -                             |
| Features | LoRA                          |
| Advanced | bfloat16                      |

### More Recipes for This Model

* [`llama3_1_8b_peft_benchmark.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_benchmark/llama3_1/llama3_1_8b_peft_benchmark.yaml)
* [`llama3_1_8b_quack_rope.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_benchmark/llama3_1/llama3_1_8b_quack_rope.yaml)
* [`llama3_1_8b_quack_rope_baseline.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_benchmark/llama3_1/llama3_1_8b_quack_rope_baseline.yaml)
* [`customizer_llama_3_1_8b_full_sft_tp.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/customizer_llama_3_1_8b_full_sft_tp.yaml)
* [`llama3_1_8b_columnmapped_lora.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/llama3_1_8b_columnmapped_lora.yaml)
* [`llama3_1_8b_hellaswag_fp8.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/llama3_1_8b_hellaswag_fp8.yaml)
* [`llama3_1_8b_hellaswag_pp.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/llama3_1_8b_hellaswag_pp.yaml)
* [`llama3_1_8b_hellaswag_pp_dynamic_seq_len.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/llama3_1_8b_hellaswag_pp_dynamic_seq_len.yaml)
* [`llama3_1_8b_instruct_squad_qlora_2node.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/llama3_1_8b_instruct_squad_qlora_2node.yaml)
* [`llama3_1_8b_squad_peft_rtx_spark.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/llama3_1/llama3_1_8b_squad_peft_rtx_spark.yaml)

## Model Reference

### Model Architecture

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

### Available Models

* [`meta-llama/Llama-3.1-8B`](https://huggingface.co/meta-llama/Llama-3.1-8B)
* [`meta-llama/Llama-3.1-8B-Instruct`](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)

## Related Resources

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