Model CoverageVision Language Models (VLMs)

Qwen2.5-VL

View as Markdown

Qwen2.5-VL is Alibaba Cloud’s vision language model series supporting image and video understanding. It features dynamic resolution processing and integrates with the Qwen2.5 language backbone.

TaskImage-Text-to-Text
ArchitectureQwen2_5VLForConditionalGeneration
Parameters2B – 72B
HF OrgQwen

Available Models

  • Qwen2.5-VL-72B-Instruct
  • Qwen2.5-VL-32B-Instruct
  • Qwen2.5-VL-7B-Instruct
  • Qwen2.5-VL-3B-Instruct
  • Qwen2-VL-7B-Instruct, Qwen2-VL-2B-Instruct (Qwen2 VL)

Architectures

  • Qwen2_5VLForConditionalGeneration — Qwen2.5-VL
  • Qwen2VLForConditionalGeneration — Qwen2-VL

Example HF Models

ModelHF ID
Qwen2.5-VL 3B InstructQwen/Qwen2.5-VL-3B-Instruct
Qwen2.5-VL 7B InstructQwen/Qwen2.5-VL-7B-Instruct
Qwen2-VL 7B InstructQwen/Qwen2-VL-7B-Instruct

Example Recipes

RecipeDatasetDescription
qwen2_5_vl_3b_rdr.yamlrdr-itemsSFT — Qwen2.5-VL 3B on RDR Items

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/qwen2_5/qwen2_5_vl_3b_rdr.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/qwen2_5/qwen2_5_vl_3b_rdr.yaml

See the Installation Guide and VLM Fine-Tuning Guide.

Fine-Tuning

See the VLM Fine-Tuning Guide.

Hugging Face Model Cards