> 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.

# Hy-MT2-30B-A3B

> Use Hy-MT2-30B-A3B with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.

[Hy-MT2-30B-A3B](https://huggingface.co/tencent/Hy-MT2-30B-A3B) is Tencent's translation Mixture-of-Experts language model with 30B total parameters and 3B activated per token. It features 48 transformer layers (layer 0 dense, layers 1-47 MoE), 128 routed experts plus 1 shared expert with top-8 sigmoid routing, Grouped Query Attention (32 Q / 4 KV heads), per-head QK RMSNorm, RoPE, and an in-forward fp32 upcast on the language-model head (`enable_lm_head_fp32`). It supports a 256K context window.

Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation).

## Fine-Tune Hy-MT2-30B-A3B

From the repository root, run:

```bash
uv run automodel --nproc-per-node=8 examples/llm_finetune/hy_mt2/hy_mt2_30b_a3b_sft.yaml
```

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

## Choose a Workflow

| Goal                                                                          | Start Here                                                                                                                                  |
| ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
| Supervised fine-tuning (SFT) - Hy-MT2-30B-A3B with FSDP2 + EP8 + fp32 LM head | Use [hy\_mt2\_30b\_a3b\_sft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/hy_mt2/hy_mt2_30b_a3b_sft.yaml). |

## Model Reference

### Model Architecture

| Property                  | Value                                     |
| ------------------------- | ----------------------------------------- |
| Task                      | Text Generation (MoE, translation)        |
| Architecture              | `HyMT2ForCausalLM`                        |
| Parameters                | 30B total / 3B activated                  |
| Hugging Face Organization | [tencent](https://huggingface.co/tencent) |

### Available Models

| Model          | HF ID                                                                     |
| -------------- | ------------------------------------------------------------------------- |
| Hy-MT2-30B-A3B | [`tencent/Hy-MT2-30B-A3B`](https://huggingface.co/tencent/Hy-MT2-30B-A3B) |

## Related Resources

* [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft)
* [Large MoE Fine-Tuning Guide](/recipes-e2e-examples/large-moe-fine-tuning)