> 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.

# Qwen2

[Qwen2](https://qwenlm.github.io/) is Alibaba Cloud's second-generation large language model series. It features grouped query attention, YARN-based long-context extension, and dual chunk attention for long sequences. QwQ-32B-Preview, a reasoning-focused model, also uses this architecture.

|                  |                                     |
| ---------------- | ----------------------------------- |
| **Task**         | Text Generation                     |
| **Architecture** | `Qwen2ForCausalLM`                  |
| **Parameters**   | 0.5B – 72B                          |
| **HF Org**       | [Qwen](https://huggingface.co/Qwen) |

## Available Models

* **Qwen2.5**: 0.5B, 1.5B, 3B, 7B, 14B, 32B, 72B
* **Qwen2**: 0.5B, 1.5B, 7B, 57B-A14B (MoE), 72B
* **QwQ-32B-Preview** — reasoning model

## Architecture

* `Qwen2ForCausalLM`

## Example HF Models

| Model                | HF ID                                                                           |
| -------------------- | ------------------------------------------------------------------------------- |
| Qwen2.5 7B Instruct  | [`Qwen/Qwen2.5-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)   |
| Qwen2.5 72B Instruct | [`Qwen/Qwen2.5-72B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) |
| Qwen2 7B Instruct    | [`Qwen/Qwen2-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-7B-Instruct)       |
| QwQ 32B Preview      | [`Qwen/QwQ-32B-Preview`](https://huggingface.co/Qwen/QwQ-32B-Preview)           |

## Example Recipes

| Recipe                                                                                                                              | Description               |
| ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------- |
| [qwen2\_5\_7b\_squad.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/qwen/qwen2_5_7b_squad.yaml)     | SFT — Qwen2.5 7B on SQuAD |
| [qwq\_32b\_squad\_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/qwen/qwq_32b_squad_peft.yaml) | LoRA — QwQ 32B on SQuAD   |

## Try with NeMo AutoModel

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

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

**2. Clone the repo** to get the example recipes:

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

**3. Run the recipe** from inside the repo:

```bash
automodel --nproc-per-node=8 examples/llm_finetune/qwen/qwen2_5_7b_squad.yaml
```

**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.** Navigate to the AutoModel directory (where the recipes are):

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

**3. Run the recipe**:

```bash
automodel --nproc-per-node=8 examples/llm_finetune/qwen/qwen2_5_7b_squad.yaml
```

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) for full SFT and LoRA instructions.

## Hugging Face Model Cards

* [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
* [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)
* [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview)