Update app.py

app.py

@@ -61,7 +61,7 @@ def create_conversational_chain(vector_store):
     load_dotenv()
     # Create llm
     llm = CTransformers(streaming=True,
-                        model = AutoModel.from_pretrained("NousResearch/Nous-Hermes-llama-2-7b"), 
+                        model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-llama-2-7b", device_map='auto',torch_dtype=torch.float16,load_in_4bit=True, token=True ), 
                         callbacks=[StreamingStdOutCallbackHandler()],
                         model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
     # llm = Replicate(