Instructions to use google/siglip2-base-patch16-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip2-base-patch16-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip2-base-patch16-224") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/siglip2-base-patch16-224", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Remove the Gemma chat template from tokenizer_config.json
SigLIP2's text tower reuses the Gemma tokenizer, and tokenizer_config.json still carries Gemma's chat_template. SigLIP2 has no chat format, so tools that honor a tokenizer's chat template wrap the text in <start_of_turn>user ... <end_of_turn> markers and drop EOS. For example, vLLM's /v1/embeddings with messages returns a different embedding than for the same plain text (11 tokens instead of 6 for "a photo of a cat"; vLLM-side fix in https://github.com/vllm-project/vllm/pull/66624).
This PR removes that one key. Tokenizer and processor output are unchanged (checked with Transformers); only apply_chat_template stops working, which has no meaning for this model.
The same template is in the other fixed-resolution SigLIP2 checkpoints, which could take the same one-line change: siglip2-base-patch16-256, -384, -512, siglip2-base-patch32-256, siglip2-large-patch16-256, -384, -512, siglip2-so400m-patch14-224, -384, siglip2-so400m-patch16-256, -384, -512, and siglip2-giant-opt-patch16-256, -384. The NaFlex checkpoints don't have it.