MobileCLIP2-S4-OpenCLIP

Model card for MobileCLIP2-S4-OpenCLIP

These weights and model card are adapted from the original Apple model at https://huggingface.co/apple/MobileCLIP2-S4. This version uses canonical OpenCLIP configs and weight naming.

MobileCLIP2 was introduced in MobileCLIP2: Improving Multi-Modal Reinforced Training (TMLR August 2025 <mark>Featured</mark>), by Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Alexander T Toshev, Oncel Tuzel, Hadi Pouransari.

This repository contains the MobileCLIP2-S4 checkpoint.

Highlights

• MobileCLIP2-S4 matches the accuracy of SigLIP-SO400M/14 with 2x fewer parameters and surpasses DFN ViT-L/14 at 2.5x lower latency measured on iPhone12 Pro Max.
• MobileCLIP-S3/S4 are our new architectures trained on MobileCLIP’s training dataset, DataCompDR-1B (dashed lines).
• Our smallest variant MobileCLIP-S0 obtains similar zero-shot performance as OpenAI's ViT-B/16 model while being 4.8x faster and 2.8x smaller.
• MobileCLIP-S2 obtains better avg zero-shot performance than SigLIP's ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples.
• MobileCLIP-B (LT) attains zero-shot ImageNet performance of 77.2% which is significantly better than recent works like DFN and SigLIP with similar architectures or even OpenAI's ViT-L/14@336.

Checkpoints and Results (Original Apple links)

How to Use

import torch
import open_clip
from PIL import Image
from urllib.request import urlopen
from timm.utils import reparameterize_model

model, _, preprocess = open_clip.create_model_and_transforms('MobileCLIP2-S4', pretrained='dfndr2b')
model.eval()
tokenizer = open_clip.get_tokenizer('MobileCLIP2-S4')

# For inference/model exporting purposes, optionally reparameterize for better performance
model = reparameterize_model(model)

image = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat", "a doughnut"])

with torch.no_grad(), torch.amp.autocast(image.device.type):
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)
    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)