> 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-3.3-70B-Instruct

> Use NeMo AutoModel to fine-tune Llama-3.3-70B-Instruct for LLM workflows with checked-in text generation recipes and documented distributed settings.

[Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `LlamaForCausalLM` architecture.

## Fine-Tune Llama-3.3-70B-Instruct

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

```bash
automodel examples/llm_finetune/llama3_3/llama_3_3_70b_instruct_squad.yaml --nproc-per-node 8
```

Use the [Slurm launcher guide](/nemo/automodel/v0.7/job-launchers/slurm-cluster) for the multi-node run.

## 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/llm_finetune/llama3_3/llama_3_3_70b_instruct_squad.yaml).             |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_benchmark/llama3_3/custom_llama3_3_70b_instruct_peft_benchmark.yaml). |

### Configuration

| Setting  | Configuration                                                                                                                        |
| -------- | ------------------------------------------------------------------------------------------------------------------------------------ |
| Hardware | -                                                                                                                                    |
| Strategy | FSDP2; tp_size=4, pp_size=2, cp_size=1                                                                                               |
| Nodes    | 4                                                                                                                                    |
| Features | Checkpointing (enabled=true), Activation checkpointing (activation_checkpointing=true), Packed sequences (packed_sequence_size=1024) |
| Advanced | bf16                                                                                                                                 |

### More Recipes for This Model

* [`custom_llama3_3_70b_instruct_peft_benchmark.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_benchmark/llama3_3/custom_llama3_3_70b_instruct_peft_benchmark.yaml)
* [`custom_llama3_3_70b_instruct_peft_benchmark_2nodes.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_benchmark/llama3_3/custom_llama3_3_70b_instruct_peft_benchmark_2nodes.yaml)
* [`llama3_3_70b_instruct_peft_benchmark.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_benchmark/llama3_3/llama3_3_70b_instruct_peft_benchmark.yaml)
* [`llama_3_3_70b_instruct_squad_peft_pp.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_benchmark/llama3_3/llama_3_3_70b_instruct_squad_peft_pp.yaml)
* [`llama_3_3_70b_instruct_squad_peft.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_finetune/llama3_3/llama_3_3_70b_instruct_squad_peft.yaml)
* [`llama_3_3_70b_instruct_squad_peft_qlora_rtx_spark.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_finetune/llama3_3/llama_3_3_70b_instruct_squad_peft_qlora_rtx_spark.yaml)
* [`llama_3_3_70b_instruct_squad_peft_qlora_spark.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/r0.7.0/examples/llm_finetune/llama3_3/llama_3_3_70b_instruct_squad_peft_qlora_spark.yaml)

## Model Reference

### Model Architecture

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

### Available Models

* [`meta-llama/Llama-3.3-70B-Instruct`](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)

## Related Resources

* [LLM fine-tuning guide](/nemo/automodel/v0.7/recipes-e2e-examples/sft-peft)