Update app.py

app.py

@@ -12,6 +12,8 @@ origins = [
     "https://articko-artickbot.hf.space/",
     "https://articko-artickbot.hf.space/api/start_conversation",
     "https://articko-artickbot.hf.space/api/get_response/",
+    "https://127.0.0.1/",
+    "https://127.0.0.1/api/",
 ]
 app.add_middleware(
     CORSMiddleware,
@@ -47,7 +49,7 @@ def load_quantized_model(model_id, model_basename):
 
 
 # Making the code device-agnostic
-model, tokenizer = load_quantized_model(model_name_or_path, "model.safetensors")
+#model, tokenizer = load_quantized_model(model_name_or_path, "model.safetensors")
 
 
 
@@ -66,6 +68,9 @@ def load_model_norm():
 
     return model, tokenizer 
 
+
+model, tokenizer = load_model_norm()
+
     
 # Function to generate a response using the model
 def generate_response(prompt: str) -> str:
@@ -105,12 +110,14 @@ def generate_response(prompt: str) -> str:
     return generated_text
 
 
+
+
+
 @app.get("/", tags=["Home"])
 async def api_home():
     return {'detail': 'Welcome to Eren Bot!'}
 
-    
-    
+        
 # Endpoint to start a new conversation thread
 @app.post('/api/start_conversation')
 async def start_conversation(request: Request):
@@ -129,6 +136,8 @@ async def start_conversation(request: Request):
 
     
 # Endpoint to get the response of a conversation thread
+
+    
 @app.get('/api/get_response/{thread_id}')
 async def get_response(thread_id: int):
     if thread_id not in conversations:
@@ -143,6 +152,8 @@ async def get_response(thread_id: int):
     return {'response': response}
 
 
+
+
 @app.post('/api/chat')
 async def chat(request: Request):
     data = await request.json()