Update README.md

README.md

@@ -46,7 +46,7 @@ Full BF16 version of the model. We recommend this variant for further fine-tunin
 
 ## Model Overview
 
-**LightOnOCR** combines a high-performance Vision Transformer encoder with a lightweight text decoder distilled from high-quality open VLMs.
+**LightOnOCR** combines a Vision Transformer encoder(Pixtral-based) with a lightweight text decoder(Qwen3-based) distilled from high-quality open VLMs.
 It is optimized for document parsing tasks, producing accurate, layout-aware text extraction from high-resolution pages.