AXERA-TECH
/

siglip2-base-patch16-224

Zero-Shot Classification

Model card Files Files and versions

wzf19947 commited on 16 days ago

Commit

ad55e40

·

1 Parent(s): 1038086

update readme

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ base_model:
 pipeline_tag: zero-shot-classification
 ---
-# SigLIP2 (shape-optimized model)
 SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.
 You can use the raw model for tasks like zero-shot image classification and image-text retrieval, or as a vision encoder for VLMs (and other vision tasks).

 pipeline_tag: zero-shot-classification
 ---
+# SigLIP2
 SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.
 You can use the raw model for tasks like zero-shot image classification and image-text retrieval, or as a vision encoder for VLMs (and other vision tasks).