Skip to content
ModelListedExternal
Download

NanoVLM HuggingFaceTB SmolLM2 135M Google Siglip Base Patch16 224 v1.2

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...

Sourcehuggingface.co/cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2/tree/a4a84a8ce62218515c1d0e7ad710b6d4883c3044
KindModelVersionRevision a4a84a8Bgrade

Model source

Kind
Model
File size
847 MB
Version
vRevision a4a84a8
Updated
Oct 30, 2026
Downloads
9
Source
Hugging Face

Source description

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("cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2")

Sources

1 source
Hugging FacePrimaryVersion a4a84a8ce62218515c1d0e7ad710b6d4883c3044
huggingface.co/cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2/tree/a4a84a8ce62218515c1d0e7ad710b6d4883c3044

Verified Oct 30

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

model.safetensors

safetensors · FP32 (tensor header) · 847 MB · SHA-256 130a677703a5…1033 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 14huggingface.co/cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2

--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards library_name: nanovlm license: mit pipeline_tag: image-text-to-text tags: - vision-language - multimodal - research --- **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: ```python from models.vision_language_model import VisionLanguageModel model = VisionLanguageModel.from_pretrained("cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2") ```

NoteOct 30huggingface.co/cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2

Source context: 9 downloads · 0 likes · Pipeline image-text-to-text · Library nanovlm · Repo cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2

NoteAug 14huggingface.co/cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2

Source context: 29 downloads · 0 likes · Pipeline image-text-to-text · Library nanovlm · Repo cultural-arts/nanoVLM-HuggingFaceTB-SmolLM2-135M-google-siglip-base-patch16-224-v1.2