This model is a smaller version of sentence-transformers/clip-ViT-B-32-multilingual-v1 optimized for Urdu language via vocabulary size reduction using the trimming method.
This trimmed model should perform similarly to the original model with only 16,384 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.

Model Statistics

Metric	Original	Trimmed	Reduction
Vocabulary size	119,547 tokens	16,384 tokens	72.59%
Model size (with visual encoder)	222,976,512 params	143,747,328 params	35.53%
Model size (without visual encoder)	135,127,296 params	55,898,112 params	58.63%

Model size (with visual encoder)

Model size (without visual encoder)

Mining Dataset Statistics

Number of texts used for mining: 119,354 texts
Dataset: lbourdois/fineweb-2-trimming

Usage

Sentence-transformers

python

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("aphaedge-ai/clip-ViT-B-32-multilingual-v1-ur-32768")
clip = SentenceTransformer("sentence-transformers/clip-ViT-B-32")

images = [
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg",
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
    "https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg"
]
texts = ["Potential label 1 in Urdu", "Potential label 2 in Urdu", "Potential label 3 in Urdu", "Potential label 4 in Urdu"]

image_embeddings = clip.encode(images)
text_embeddings = model.encode(texts)
print(image_embeddings.shape, text_embeddings.shape)

similarities = model.similarity(image_embeddings, text_embeddings)
print(similarities)

Citations

clip-vit-b-32-multilingual-v1

Hugging Face repo: https://huggingface.co/sentence-transformers/clip-ViT-B-32-multilingual-v1

Trimming blog post

@misc{hf_blogpost_trimming,
      title={Introduction to Trimming}, 
      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
      year={2026},
      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
}

alphaedge-ai/clip-ViT-B-32-multilingual-v1-ur-16384

clip-ViT-B-32-multilingual-v1-ur-16384