Update app.py

app.py

@@ -10,13 +10,16 @@ from langchain.memory import ConversationBufferMemory
 # Configuración del modelo de lenguaje
 MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.3"
 device = "cuda" if torch.cuda.is_available() else "cpu"
+HF_TOKEN = os.getenv("HF_TOKEN")  # Obtiene el token de la variable de entorno
 
 print("🔄 Cargando modelo de lenguaje...")
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME,
+  use_auth_token=HF_TOKEN                                        )
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     torch_dtype=torch.float16 if device == "cuda" else torch.float32,
-    device_map="auto"
+    device_map="auto",
+ use_auth_token=HF_TOKEN
 ).to(device)
 
 # Memoria conversacional