Update README.md

README.md

@@ -1,29 +1,29 @@
 ---
-license: llama3.2
+license: llama3
 inference: false
 tags:
 - green
-- p1
+- p8
 - llmware-chat
 - ov
 ---
 
-# llama-3.2-1b-instruct-ov
+# openchat-3.6-8b-20240522-ov
 
-**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.    
+**openchat-3.6-8b-202440522-ov** is an OpenVino int4 quantized version of OpenChat-3.6-8b-20240522, providing a 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 new 1B chat foundation model from Meta. 
+[**openchat-3.6-8b-202440522**](https://huggingface.co/openchat/openchat-3.6-8b-20240522) which is a popular leading chat finetuning of Llama 3. 
 
 
 ### Model Description
 
-- **Developed by:** meta-llama
+- **Developed by:** openchat
 - **Quantized by:** llmware
-- **Model type:** llama-3.2 
-- **Parameters:** 1 billion
-- **Model Parent:** meta-llama/Meta-Llama-3.2-1B-Instruct  
+- **Model type:** llama-3
+- **Parameters:** 8 billion
+- **Model Parent:** openchat/openchat-3.6-8b-20240522 
 - **Language(s) (NLP):** English  
-- **License:** Llama 3.2 Community License
+- **License:** Llama 3 Community License
 - **Uses:** General chat use cases 
 - **RAG Benchmark Accuracy Score:** NA  
 - **Quantization:** int4  
@@ -35,4 +35,4 @@ tags:
 
 [llmware on hf](https://www.huggingface.co/llmware)  
 
-[llmware website](https://www.llmware.ai)
+[llmware website](https://www.llmware.ai)