Update README.md

README.md

@@ -21,10 +21,10 @@ pipeline_tag: image-text-to-text
 
 ### Model Description
 
-We are happy to share the EraX-VL-7B-v1 model, a powerful multimodal model in OCR (optical character recognition) and VQA (video question-answering) across multiple languages but especially in Vietnamese.
-One of the strengths of the EraX-VL-7B is its ability to accurately recognize forms, invoices, bills of sale, quotes, and medical records, among other things, which we believe will be very convenient for Hospitals, Clinics, Insurance Companies, and other applications.
+We are happy to share the EraX-VL-7B-v1 model, a powerful multimodal model in OCR (optical character recognition) and VQA (vision question-answering) across multiple languages but especially in Vietnamese.
+One of the strengths of the EraX-VL-7B is its ability to accurately recognize medical forms of all kinds, invoices, bills of sale, quotes, and medical records, among other things, which we believe will be very convenient for Hospitals, Clinics, Insurance Companies, and other applications.
 EraX-VL-7B has been finetuned from the base Qwen/Qwen2-VL-7B-Instruct which we found to be of good quality and quite fluent in Vietnamese.
-We will continue to develop better versions, as well as share benchmarks in the near future.
+We will continue to develop and release better versions for free use, as well as share benchmarks in the near future.
 
 EraX-VL-7B-V1 is a young member of our EraX's LànhGPT repository of LLM models.