Update app.py

app.py

@@ -9,8 +9,8 @@ from transformers import is_torch_npu_available
 from threading import Thread
 
 
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-14B-Chat")
-model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-14B-Chat", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-7B-Chat")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-7B-Chat", torch_dtype=torch.bfloat16)
 if is_torch_npu_available():
     model.to("npu:0")
 elif torch.cuda.is_available():