Update gradio_app.py

gradio_app.py

@@ -7,13 +7,13 @@ import psutil
 # Initing things                
 print("! INITING LLAMA MODEL !")
 llm = Llama(model_path="./model.bin")                              # LLaMa model
-llama_model_name = "TheBloke/openchat_3.5-GGUF" 
+llama_model_name = "NousResearch/Hermes-2-Pro-Mistral-7B-GGUF"     # This is just for indication in "three dots menu" 
 print("! INITING DONE !")
 
 # Preparing things to work
 title = "llama.cpp API"
 desc = '''<h1>Hello, world!</h1>
-This is showcase how to make own server with Llama2 model.<br>
+This is showcase how to make own server with Llama2 model using llama_cpp.<br>
 I'm using here 7b model just for example. Also here's only CPU power.<br>
 But you can use GPU power as well!<br><br>
 <h1>How to GPU?</h1>