Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 
 **llama-3.2-1b-instruct-ov** is an OpenVino int4 quantized version of Llama 3.2 1B Instruct, providing a very small, very fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    
 
-[**llama-3.2-1b-instruct**](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) is a leading open source general foundation model from Meta. 
+[**llama-3.2-1b-instruct**](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) is a new 1B chat foundation model from Meta. 
 
 
 ### Model Description