Update app.py

app.py

@@ -5,8 +5,10 @@ from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStr
 from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
-tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
-model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+# model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+model_name = "scutcyr/BianQue-2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
@@ -56,7 +58,7 @@ def predict(message, history):
 
 # Setting up the Gradio chat interface.
 gr.ChatInterface(predict,
-                 title="Tinyllama_chatBot",
-                 description="Ask Tiny llama any questions",
-                 examples=['How to cook a fish?', 'Who is the president of US now?']
+                 title="TCM_ChatBLM_chatBot",
+                 description="Ask TCM_ChatBLM_chatBot any questions",
+                 examples=['你好，我最近失眠，可以怎麼解決?', '請問有沒有跌打藥可以用？']
                  ).launch()  # Launching the web interface.