Update app.py

app.py

@@ -26,7 +26,7 @@ def load_model_norm():
     model_name_or_path = "TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ"
     # To use a different branch, change revision
     # For example: revision="main"
-    model = AutoModelForCausalLM.from_pretrained(model_name_or_path,device_map="auto", trust_remote_code=True,revision="gptq-4bit-32g-actorder_True")
+    model = AutoModelForCausalLM.from_pretrained(model_name_or_path,device_map="auto", trust_remote_code=True,revision="gptq-4bit-128g-actorder_True")
     # Switch to CPU inference
     #model.to("cuda")
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -40,7 +40,7 @@ model, tokenizer = load_model_norm()
 app = FastAPI(root_path="/api/v1")
 
 #Generates a response from the model   
-def generate_response(prompt: str) -> dict:
+def generate_response(prompt: str) -> str:
     # Define the user prompt
     user_prompt = f'USER: {prompt}'