Update app.py

app.py

@@ -6,10 +6,10 @@ from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
 # model_name_or_path = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
-model_name_or_path = "scutcyr/BianQue-1.0"
+model_name_or_path = "Flmc/DISC-MedLLM"
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path,trust_remote_code=True)
 # model = AutoModelForCausalLM.from_pretrained(model_name,trust_remote_code=True)
-model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True).half()
+model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True)
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')