Update app.py

app.py

@@ -25,7 +25,7 @@ model = AutoModelForCausalLM.from_pretrained(
     model_name,
     quantization_config=quantization_config,
     device_map="auto",
-    max_memory={0: "22GiB", "cpu": "6GiB"}  # Prevent VRAM overflow
+    max_memory={0: "22GiB", "cpu": "6GiB"}  # Prevent VRAM overflow 
 )
 text_generator = pipeline("text-generation", model=model, tokenizer=tokenizer)