Update app.py

app.py

@@ -92,7 +92,7 @@ def create_chain(_retriever):
     n_batch = 512  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
 
     llm = LlamaCpp(
-            model_path="models/mistral-7b-instruct-v0.1.Q5_0.gguf",
+            model_path="models /mistral-7b-instruct-v0.1.Q5_0.gguf",
             n_gpu_layers=n_gpu_layers,
             n_batch=n_batch,
             n_ctx=2048,