Update main.py

main.py

@@ -16,12 +16,12 @@ app.add_middleware(
     allow_headers=['*'],
 )
 
-model_name = "unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit"
+model_name = "Qwen/Qwen2.5-0.5B-Instruct"
 print("Loading model...")
 
-# Load model directly
-tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit")
-model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit")
+# Load model directly - simple approach for HF Spaces
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Set pad token if not exists
 if tokenizer.pad_token is None: