Update app.py

app.py

@@ -4,6 +4,7 @@ from langchain.llms import HuggingFaceHub
 # Function to return the response
 def generate_answer(query):
     llm = HuggingFaceHub(
+        model_class="goliath-120b.Q4_K_M.gguf",
         repo_id="alpindale/goliath-120b",
         model_kwargs={"temperature": 0.5, "max_length": 64, "max_new_tokens": 512},
         task = "text2text-generation"