Update README.md

README.md

@@ -1,15 +1,16 @@
 ---
 license: apache-2.0
 inference: false 
+tags: [green, p1, llmware-fx,ov]
 ---
 
-# bling-tiny-llama-ov
+# slim-sentiment-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.    
+**slim-sentiment-ov** is an OpenVino int4 quantized version of slim sentiment 1B, 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.  
+[**slim-sentiment**](https://huggingface.co/llmware/slim-sentiment) is a function-calling specialized model finetuned to evaluate sentiment and return a python dictionary with a sentiment key and the classification value, e.g., "positive", "negative", or "neutral".    
 
 Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino) 
 
@@ -21,11 +22,11 @@ Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmwa
 - **Developed by:** llmware  
 - **Model type:** tinyllama  
 - **Parameters:** 1.1 billion
-- **Model Parent:** llmware/bling-tiny-llama-v0  
+- **Model Parent:** llmware/slim-sentiment
 - **Language(s) (NLP):** English  
 - **License:** Apache 2.0  
-- **Uses:** Fact-based question-answering  
-- **RAG Benchmark Accuracy Score:** 86.5  
+- **Uses:** Sentiment classification
+- **RAG Benchmark Accuracy Score:** NA  
 - **Quantization:** int4