> 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.

# Muse-Glimmer-30B

> Use NeMo AutoModel to fine-tune Muse-Glimmer-30B for LLM workflows with checked-in text generation recipes and documented distributed settings.

[Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `MuseGlimmerForConditionalGeneration` architecture.

## Fine-Tune Muse-Glimmer-30B

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

```bash
automodel \
  examples/llm_finetune/muse_glimmer/muse_glimmer_30b_tulu3_te_tp2_cp4_packed_16k.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/muse_glimmer/muse_glimmer_30b_tulu3_te_tp2_cp4_packed_16k.yaml). |
| Prepare your environment              | Follow the [installation instructions](/get-started/installation).                                                                                                       |

### Configuration

| Setting  | Configuration                                                                                                                  |
| -------- | ------------------------------------------------------------------------------------------------------------------------------ |
| Hardware | -                                                                                                                              |
| Strategy | FSDP2; tp\_size=2, pp\_size=1, cp\_size=4, ep\_size=1                                                                          |
| Nodes    | 1                                                                                                                              |
| Features | Activation checkpointing (activation\_checkpointing=true), Packed sequences (packed\_sequence\_size=16384), Transformer Engine |
| Advanced | bfloat16, attention=te, sequence length 1024                                                                                   |

## Model Reference

### Model Architecture

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

### Available Models

* [`meta-models/Muse-Glimmer-30B`](https://huggingface.co/meta-models/Muse-Glimmer-30B)

## Related Resources

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