Build Update

main.py

@@ -7,7 +7,7 @@ app = FastAPI()
 
 MODEL_ID = "ibm-granite/granite-3.3-2b-instruct"
 
-# Load tokenzier and model
+# Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
@@ -15,8 +15,8 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
 
-# Use pipeline for easier text generation
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+# Use pipeline for easier text generation (device argument removed!)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 @app.get("/", response_class=HTMLResponse)
 def index():