Update README.md

README.md

@@ -4,13 +4,13 @@ inference: false
 tags: [green, p7, llmware-chat, ov]
 ---
 
-# bling-tiny-llama-ov
+# zephyr-mistral-7b-chat-ov
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**bling-tiny-llama-ov** is an OpenVino int4 quantized version of BLING Tiny-Llama 1B, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    
+**zephyr-mistral-7b-chat-ov** is an OpenVino int4 quantized version of Zephyr-Mistral-7B-Chat, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    
 
-[**bling-tiny-llama**](https://huggingface.co/llmware/bling-tiny-llama-v0) is a fact-based question-answering model, optimized for complex business documents.  
+[**zephyr-mistral-7b-chat**](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) is a leading chat fine-tune of Mistral. 
 
 Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino) 
 
@@ -19,14 +19,14 @@ Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmwa
 
 ### Model Description
 
-- **Developed by:** llmware  
-- **Model type:** tinyllama  
-- **Parameters:** 1.1 billion
-- **Model Parent:** llmware/bling-tiny-llama-v0  
+- **Developed by:** Huggingface + Mistral 
+- **Model type:**  Mistral  
+- **Parameters:** 7 billion
+- **Model Parent:**   HuggingFaceH4/zephyr-7b-beta
 - **Language(s) (NLP):** English  
 - **License:** Apache 2.0  
-- **Uses:** Fact-based question-answering  
-- **RAG Benchmark Accuracy Score:** 86.5  
+- **Uses:** General purpose chat
+- **RAG Benchmark Accuracy Score:** NA 
 - **Quantization:** int4