SigLIP2

Install

SigLIP2 needs its own extra, which pulls in the SentencePiece package its multilingual tokenizer uses.

pip install "libreyolo[siglip2]"

Predict

Weights download from Hugging Face on first use and are cached locally.

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreSigLIP2b16-cls.pt")model.set_classes(["a forklift", "an empty aisle", "a spill"])result = model(SAMPLE_IMAGE, save=True) print(model.names[result.probs.top1], float(result.probs.top1conf))

# With no set_classes() call, CLI predict uses the 1,000 ImageNet# class names the model loads with by default.libreyolo predict model=LibreSigLIP2b16-cls.pt source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/parkour.jpg save=True

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreSigLIP2b16-cls.pt")model.set_classes(["a dog", "a cat", "outdoors"], multi_label=True)r = model(SAMPLE_IMAGE) # Independent per-class probabilities: more than one, or none, can# score high at once. Softmax (the default) instead normalizes them# into a single-label distribution, matching LibreCLIP's behavior.for i, name in model.names.items():    print(name, float(r.probs.data[i]))

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreSigLIP2b16-cls.pt", task="embed")image_embed = model(SAMPLE_IMAGE).embeddings.datatext_embed = model.embed_text("a photo of a forklift") # Both are L2-normalized, so a plain dot product is cosine similarity.similarity = (image_embed @ text_embed.T).item()

set_classes() is the one primitive that makes this an open-vocabulary classifier: it renders each label into every prompt template, encodes and averages the results, and caches the resulting [K, D] matrix as the classifier head, so it is not recomputed per image. Call it again to change classes at any time. With no call, LibreSigLIP2 loads with the 1,000 ImageNet-1k class names already set.

SigLIP scores each class independently: logit = scale * (image . text) + bias. By default that logit set is still passed through a softmax, giving a single-label distribution that matches LibreCLIP's top1/top5 behavior. Passing multi_label=True to set_classes() (or at construction) switches to independent sigmoid probabilities instead, so more than one class, or none, can score high on the same image. The tokenizer is a multilingual SentencePiece model (Gemma vocabulary), so class names in languages other than English work the same way.

With task="embed", prediction returns one L2-normalized image vector per input instead of class probabilities, and embed_text() returns normalized text rows in the same vector space, so a plain dot product between them is cosine similarity. iou has no effect on either task; there is no NMS step. See prediction for sources, streaming and result handling.

Validate

val() reads the class-folder names under an ImageFolder train/ split, calls set_classes() with them, then measures zero-shot top-1 and top-5 accuracy under softmax scoring. Accuracy depends on how the class names read as prompts, not on any weight update, since there is nothing to train. Validation only covers task="classify"; task="embed" has no dataset validator.

from libreyolo import LibreYOLO model = LibreYOLO("LibreSigLIP2b16-cls.pt") # data is an ImageFolder root with a train/ split; its folder names# become the zero-shot class prompts for this run.metrics = model.val(data="imagenette160") print(metrics["metrics/accuracy_top1"])print(metrics["metrics/accuracy_top5"])

libreyolo val model=LibreSigLIP2b16-cls.pt data=imagenette160

Export

Export bakes the model's current state into a fixed graph. For task="classify", whatever labels set_classes() last set, and the resolution at export time, are baked into a final linear layer with the learned scale and bias, so the exported graph is an ordinary [B, K] image classifier with no text tower and no tokenizer; export again after changing the classes or the size. Exporting in multi_label=True mode is not implemented; set it back to False first. task="embed" export traces the image tower alone. Both need ONNX opset 14 or higher, which the exporter sets by default.

from libreyolo import LibreYOLO model = LibreYOLO("LibreSigLIP2b16-cls.pt")model.set_classes(["a forklift", "an empty aisle", "a spill"])model.export(format="onnx") # The current set_classes() labels and the input resolution are baked# into the graph. Re-export after changing either one. multi_label# must be False (the default) at export time.

# No set_classes() call here, so this bakes in the default 1,000# ImageNet classes the model loads with.libreyolo export model=LibreSigLIP2b16-cls.pt format=onnx

from libreyolo import LibreYOLO # task="embed" traces the image tower alone; no classes needed.model = LibreYOLO("LibreSigLIP2b16-cls.pt", task="embed")model.export(format="onnx")

Checkpoints

Every published weight file for this family. Both are converted from Google's Apache-2.0 siglip2-base-patch16-256 and siglip2-so400m-patch14-384 checkpoints, not from any COCO training run.

Licensing

Citation

@misc{tschannen2025siglip2multilingualvisionlanguage,
      title={SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features}, 
      author={Michael Tschannen and Alexey Gritsenko and Xiao Wang and Muhammad Ferjad Naeem and Ibrahim Alabdulmohsin and Nikhil Parthasarathy and Talfan Evans and Lucas Beyer and Ye Xia and Basil Mustafa and Olivier Hénaff and Jeremiah Harmsen and Andreas Steiner and Xiaohua Zhai},
      year={2025},
      eprint={2502.14786},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2502.14786}, 
}