Update app.py

app.py

@@ -7,10 +7,7 @@ from transformers import (AutoModelForCausalLM, AutoTokenizer, LlamaForCausalLM,
 
 app = FastAPI()
 
-if torch.cuda.is_available():
-    print("CUDA is available. GPU will be used.")
-else:
-    print("CUDA is not available. CPU will be used.")
+    
 # Load the model and tokenizer
 model_name_or_path = "TheBloke/Wizard-Vicuna-7B-Uncensored-GPT/"
 # Dictionary to store conversation threads and their context