> 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.

# ERNIE-4.5-21B-A3B-PT

> Use NeMo AutoModel to fine-tune ERNIE-4.5-21B-A3B-PT for LLM workflows with checked-in text generation recipes and documented distributed settings.

[ERNIE-4.5-21B-A3B-PT](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `Ernie4_5_MoeForCausalLM` architecture.

## Fine-Tune ERNIE-4.5-21B-A3B-PT

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

```bash
automodel examples/llm_finetune/ernie4_5/ernie4_5_21b_a3b_hellaswag.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/ernie4_5/ernie4_5_21b_a3b_hellaswag.yaml). |
| Prepare your environment              | Follow the [installation instructions](/get-started/installation).                                                                                 |

### Configuration

| Setting  | Configuration                                                                                                                           |
| -------- | --------------------------------------------------------------------------------------------------------------------------------------- |
| Hardware | -                                                                                                                                       |
| Strategy | FSDP2; tp\_size=1, pp\_size=1, cp\_size=1, ep\_size=8                                                                                   |
| Nodes    | -                                                                                                                                       |
| Features | Checkpointing (enabled=true), Activation checkpointing (activation\_checkpointing=true), Transformer Engine, DeepEP (dispatcher=deepep) |
| Advanced | bfloat16, attention=te, linear=torch, experts=torch\_mm, dispatcher=deepep                                                              |

## Model Reference

### Model Architecture

| Property     | Value                     |
| ------------ | ------------------------- |
| Task         | Text generation           |
| Architecture | `Ernie4_5_MoeForCausalLM` |

### Available Models

* [`baidu/ERNIE-4.5-21B-A3B-PT`](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT)

## Related Resources

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