Model CoverageOmni Models

Phi-4-multimodal

View as Markdown

Phi-4-multimodal-instruct is Microsoft’s multimodal extension of Phi-4, supporting text, image, and audio inputs — making it suitable for speech, vision, and combined multimodal tasks.

TaskOmnimodal (Text·Image·Audio)
ArchitecturePhi4MultimodalForCausalLM
Parameters5.6B
HF Orgmicrosoft

Available Models

  • Phi-4-multimodal-instruct: 5.6B

Architecture

  • Phi4MultimodalForCausalLM

Example HF Models

ModelHF ID
Phi-4-multimodal-instructmicrosoft/Phi-4-multimodal-instruct

Example Recipes

RecipeDatasetDescription
phi4_mm_cv17.yamlCommonVoice 17SFT — Phi-4-multimodal on CommonVoice (audio-text)

Try with NeMo AutoModel

1. Install (full instructions):

$pip install nemo-automodel

2. Clone the repo to get the example recipes:

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

3. Run the recipe from inside the repo:

$automodel --nproc-per-node=8 examples/vlm_finetune/phi4/phi4_mm_cv17.yaml

1. Pull the container and mount a checkpoint directory:

$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):

$cd /opt/Automodel

3. Run the recipe:

$automodel --nproc-per-node=8 examples/vlm_finetune/phi4/phi4_mm_cv17.yaml

See the Installation Guide and Omni Fine-Tuning Guide.

Fine-Tuning

See the VLM / Omni Fine-Tuning Guide.

Hugging Face Model Cards