> 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.

# DeepSeek-V3.2

> Use NeMo AutoModel to fine-tune DeepSeek-V3.2 for LLM workflows with checked-in text generation recipes and documented distributed settings.

[DeepSeek-V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `DeepseekV32ForCausalLM` architecture.

## Fine-Tune DeepSeek-V3.2

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

```bash
automodel examples/llm_benchmark/deepseek/dsv32_lora.yaml --nproc-per-node 8
```

Use the [Slurm launcher guide](/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/main/examples/llm_benchmark/deepseek/dsv32_lora.yaml). |
| Prepare your environment              | Follow the [installation instructions](/get-started/installation).                                                                  |

### Configuration

| Setting  | Configuration                                                                                                   |
| -------- | --------------------------------------------------------------------------------------------------------------- |
| Hardware | -                                                                                                               |
| Strategy | FSDP2; tp\_size=1, pp\_size=4, cp\_size=1, ep\_size=32                                                          |
| Nodes    | 16                                                                                                              |
| Features | Activation checkpointing (activation\_checkpointing=true), LoRA, Transformer Engine, DeepEP (dispatcher=deepep) |
| Advanced | attention=te, linear=te, experts=gmm, dispatcher=deepep                                                         |

## Model Reference

### Model Architecture

| Property     | Value                    |
| ------------ | ------------------------ |
| Task         | Text generation          |
| Architecture | `DeepseekV32ForCausalLM` |

### Available Models

* [`deepseek-ai/DeepSeek-V3.2`](https://huggingface.co/deepseek-ai/DeepSeek-V3.2)

## Related Resources

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