Update app.py

app.py

@@ -21,7 +21,8 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "SeaLLMs/med-seallm3-7b-sftv2-department-recommend"
+#model_id = "SeaLLMs/med-seallm3-7b-sftv2-department-recommend"
+model_id = "SeaLLMs/debug_6"
 
 tokenizer = Qwen2TokenizerFast.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(