Update app.py

app.py

@@ -5,7 +5,7 @@ from langchain.llms import CTransformers
 ## Function to get response from llama 2 model
 def getllamaresponse(prompt_template):
     # LLama2 model
-    llm = CTransformers(model='/workspaces/Personal-AI/llama-2-7b-chat.ggmlv3.q8_0.bin',
+    llm = CTransformers(model='https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B',
                         model_type='llama',
                         config={"max_new_tokens": 300, "temperature": 0.01})