Update app.py

app.py

@@ -140,9 +140,9 @@ async def load_model_async(model_name: str):
     if model_name == "model_1":
         return VLLM("Hjgugugjhuhjggg/llama-3.2-1B-spinquant-hf", device=device, max_model_len=max_model_len)
     elif model_name == "model_2":
-        return VLLM("meta-llama/Llama-3.2-1B", device=device, max_model_len=max_model_len)
+        return VLLM("Qwen/Qwen2.5-Coder-1.5B", device=device, max_model_len=max_model_len)
     elif model_name == "model_3":
-        return VLLM("Qwen2.5-3B-Instruct", device=device, max_model_len=max_model_len)
+        return VLLM("Qwen/Qwen2.5-3B-Instruct", device=device, max_model_len=max_model_len)
     elif model_name == "model_4":
         return VLLM("gpt2", device=device, max_model_len=max_model_len)
     return None