Update README.md

README.md

@@ -7,6 +7,27 @@ license: mit
 
 
 
+
+## To use this model directly import the following
+
+```
+from llama_cpp import Llama
+
+llm = Llama.from_pretrained(
+	repo_id="Omarrran/gemma2_model_9B_q4_km",
+	filename="unsloth.Q4_K_M.gguf",
+)
+
+```
+
+ To know more about how to use llama_cpp Inferenece mode  see here : [Link to llama_cpp](https://github.com/ggerganov/llama.cpp)
+
+
+
+
+
+
+
 ----------------------------------------------
 
 # llama.cpp Conversion, Quantization, & Merging