Update app.py

app.py

@@ -8,7 +8,7 @@ model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"  # A great smaller chat model
 # Load tokenizer and create pipeline
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
-    model=model_name,
+    model_name,
     torch_dtype=torch.float16,
     device_map="auto"  # Uses GPU if available, falls back to CPU
 )