> 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.

# Phi

[Microsoft's Phi](https://azure.microsoft.com/en-us/products/phi) are compact, high-capability language models designed to punch above their weight class. Phi-1.5 and Phi-2 use a standard transformer decoder architecture (`PhiForCausalLM`). For Phi-3 and Phi-4 see [Phi-3 / Phi-4](/model-coverage/large-language-models/phi-3-phi-4).

|                  |                                               |
| ---------------- | --------------------------------------------- |
| **Task**         | Text Generation                               |
| **Architecture** | `PhiForCausalLM`                              |
| **Parameters**   | 1.3B – 2.7B                                   |
| **HF Org**       | [microsoft](https://huggingface.co/microsoft) |

## Available Models

* **Phi-2**: 2.7B
* **Phi-1.5**: 1.3B

## Architecture

* `PhiForCausalLM`

## Example HF Models

| Model   | HF ID                                                           |
| ------- | --------------------------------------------------------------- |
| Phi-2   | [`microsoft/phi-2`](https://huggingface.co/microsoft/phi-2)     |
| Phi-1.5 | [`microsoft/phi-1_5`](https://huggingface.co/microsoft/phi-1_5) |

## Example Recipes

| Recipe                                                                                                                         | Description           |
| ------------------------------------------------------------------------------------------------------------------------------ | --------------------- |
| [phi\_2\_squad.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/phi/phi_2_squad.yaml)            | SFT — Phi-2 on SQuAD  |
| [phi\_2\_squad\_peft.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/phi/phi_2_squad_peft.yaml) | LoRA — Phi-2 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/phi/phi_2_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:26.04.00
```

**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/phi/phi_2_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).

## Hugging Face Model Cards

* [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
* [microsoft/phi-1\_5](https://huggingface.co/microsoft/phi-1_5)