Update README.md

README.md

@@ -1,16 +1,16 @@
 ---
 license: apache-2.0
 inference: false 
-tags: [green, llmware-rag, p3,ov]
+tags: [green, llmware-rag, p1,ov]
 ---
 
-# bling-phi-3-ov
+# bling-qwen-500m-ov
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**bling-phi-3-ov** is an OpenVino int4 quantized version of BLING Phi-3, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU. 
+**bling-qwen-500m-ov** is an OpenVino int4 quantized version of BLING Qwen 500m, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU. 
 
-[**bling-phi-3**](https://huggingface.co/llmware/bling-phi-3) is a fact-based question-answering model, optimized for complex business documents. 
+[**bling-qwen-500m**](https://huggingface.co/llmware/bling-qwen-500m) is a fact-based question-answering model, optimized for complex business documents. 
 
 Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino) 
 
@@ -20,13 +20,13 @@ Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmwa
 ### Model Description
 
 - **Developed by:** llmware 
-- **Model type:** phi3 
-- **Parameters:** 3.8 billion
-- **Model Parent:** llmware/bling-phi-3 
+- **Model type:** qwen2 
+- **Parameters:** 0.5 billion
+- **Model Parent:** llmware/bling-qwen-500m 
 - **Language(s) (NLP):** English 
 - **License:** Apache 2.0 
 - **Uses:** Fact-based question-answering 
-- **RAG Benchmark Accuracy Score:** 99.5 
+- **RAG Benchmark Accuracy Score:** [80]
 - **Quantization:** int4