Update app.py

app.py

@@ -6,13 +6,13 @@ import torch
 
 class YourModel:
     def __init__(self):
-        Tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-1_8B-Chat", trust_remote_code=True)
-        model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-1_8B-Chat", device_map="auto", trust_remote_code=True).eval()
-        history = None
+        self.tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-1_8B-Chat", trust_remote_code=True)
+        self.model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-1_8B-Chat", device_map="auto", trust_remote_code=True).eval()
+        self.history = None
 
     @instrument
     def predict(self, user_input, system_prompt):
-        print("Model response for: " + user_input + " with prompt: " + system_prompt")
+        print("Model response for:" + user_input + " with prompt:" + system_prompt)
         response, self.history = model.chat(tokenizer, user_input, history=self.history, system=system_prompt)
         return response