Update README.md

README.md

@@ -22,7 +22,7 @@ tags:
 **What's new in ColVintern-1B-v1!**
 - We coded and successfully trained the **Colpali pipeline** for Vintern. The model supports RAG by extracting vector embeddings for questions and images containing related information.
 - This is the first experimental version, trained on the [**Colpali dataset**](https://huggingface.co/datasets/vidore/colpali_train_set) for English and **5%** of the image-based question-answer pairs we have for Vietnamese.
-- The model achieves results nearly equivalent to Colpali version 1, with strong support for Vietnamese texts and only 1 billion parameters compared to current Colpali models.
+- The model achieves results nearly equivalent to Colpali version 1, with strong support for Vietnamese texts and only 1 billion parameters compared to current 2B-3B Colpali models.
 
 ## Colpali Benchmarks