Update README.md

README.md

@@ -1,26 +1,26 @@
 ---
 license: apache-2.0
 inference: false 
-tags: [green, llmware-rag, p1, ov]
+tags: [green, llmware-rag, p3, ov]
 ---
 
-# bling-tiny-llama-ov
+# bling-phi-3-ov
 
-**bling-tiny-llama-ov** is a very small, very fast fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, and quantized and packaged in OpenVino int4 for AI PCs using Intel GPU, CPU and NPU.    
+**bling-phi-3-ov** is a fast and accurate fact-based question-answering model, designed for retrieval augmented generation (RAG) with complex business documents, and quantized and packaged in OpenVino int4 for AI PCs using Intel GPU, CPU and NPU.    
 
-This model is one of the smallest and fastest in the series.  For higher accuracy, look at larger models in the BLING/DRAGON series.    
+This model is one of the most accurate in the BLING/DRAGON model series, which is especially notable given the relative small size and is ideal for use on AI PCs and local inferencing.  
 
 ### Model Description
 
 - **Developed by:** llmware  
-- **Model type:** tinyllama  
-- **Parameters:** 1.1 billion  
+- **Model type:** phi-3
+- **Parameters:** 3.8 billion  
 - **Quantization:** int4  
-- **Model Parent:** [llmware/bling-tiny-llama-v0](https://www.huggingface.co/llmware/bling-tiny-llama-v0)    
+- **Model Parent:** [llmware/bling-phi-3](https://www.huggingface.co/llmware/bling-phi-3)    
 - **Language(s) (NLP):** English  
 - **License:** Apache 2.0  
 - **Uses:** Fact-based question-answering, RAG  
-- **RAG Benchmark Accuracy Score:** 86.5  
+- **RAG Benchmark Accuracy Score:** 99.5
 
     
 Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino)