library_name: nanovlm
license: mit
pipeline_tag: image-text-to-text
tags:
- vision-language
- multimodal
- research
Introduction
You can find the history behind this work in this blog post: https://www.gradients.zone/blog/a-super-small-vision-language-model/
datasets
- "localized_narratives" part from the_cauldron (200k items)
- private dataset (30k items)
nanoVLM is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of code. It combines a ViT-based image encoder (SigLIP-B/16-224-85M) with a lightweight causal language model (SmolLM2-135M), resulting in a compact 222M parameter model.
For more information, check out the base model on https://huggingface.co/lusxvr/nanoVLM-222M.
Usage:
Clone the nanoVLM repository: https://github.com/huggingface/nanoVLM. Follow the install instructions and run the following code:
from models.vision_language_model import VisionLanguageModel
model = VisionLanguageModel.from_pretrained("sbrzz/nanoVLM")