> 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.

# StarCoder

[StarCoder](https://huggingface.co/blog/starcoder) is BigCode's code language model trained on the Stack dataset. It uses Multi-Query Attention and Fill-in-the-Middle (FIM) objectives. WizardCoder also uses this architecture.

|                  |                                           |
| ---------------- | ----------------------------------------- |
| **Task**         | Code Generation                           |
| **Architecture** | `GPTBigCodeForCausalLM`                   |
| **Parameters**   | 1B – 15.5B                                |
| **HF Org**       | [bigcode](https://huggingface.co/bigcode) |

## Available Models

* **StarCoder**: 15.5B
* **gpt\_bigcode-santacoder**: 1.1B
* **WizardCoder-15B-V1.0** (WizardLM)

## Architecture

* `GPTBigCodeForCausalLM`

## Example HF Models

| Model           | HF ID                                                                                     |
| --------------- | ----------------------------------------------------------------------------------------- |
| StarCoder       | [`bigcode/starcoder`](https://huggingface.co/bigcode/starcoder)                           |
| SantaCoder      | [`bigcode/gpt_bigcode-santacoder`](https://huggingface.co/bigcode/gpt_bigcode-santacoder) |
| WizardCoder 15B | [`WizardLM/WizardCoder-15B-V1.0`](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0)   |

## Try with NeMo AutoModel

Install NeMo AutoModel and follow the fine-tuning guide to configure a recipe for this model.

**1. Install** ([full instructions](/get-started/installation)):

```bash
pip install nemo-automodel
```

**2. Clone the repo** to get example recipes you can adapt:

```bash
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
```

**3. Fine-tune** by adapting a base LLM recipe — override the model ID on the CLI:

```bash
automodel --nproc-per-node=8 examples/llm_finetune/llama3_2/llama3_2_1b_squad.yaml \
  --model.pretrained_model_name_or_path <MODEL_HF_ID>
```

Replace `<MODEL_HF_ID>` with the model ID from **Example HF Models** above.

**1. Pull the container** and mount a checkpoint directory:

```bash
docker run --gpus all -it --rm \
  --shm-size=8g \
  -v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
  nvcr.io/nvidia/nemo-automodel:26.06.00
```

**2.** The recipes are at `/opt/Automodel/examples/` — navigate there:

```bash
cd /opt/Automodel
```

**3. Fine-tune**:

```bash
automodel --nproc-per-node=8 examples/llm_finetune/llama3_2/llama3_2_1b_squad.yaml \
  --model.pretrained_model_name_or_path <MODEL_HF_ID>
```

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

## Fine-Tuning

See the [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft).

## Hugging Face Model Cards

* [bigcode/starcoder](https://huggingface.co/bigcode/starcoder)