Update handler.py

handler.py

@@ -9,13 +9,13 @@ dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.
 class EndpointHandler:
     def __init__(self, path=""):
         # load the model
-        this.tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-13B-Chat", use_fast=False, trust_remote_code=True)
-        this.model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", device_map="auto", torch_dtype=dtype, trust_remote_code=True)
-        this.model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan-13B-Chat")
+        self.tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan-13B-Chat", use_fast=False, trust_remote_code=True)
+        self.model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan-13B-Chat", device_map="auto", torch_dtype=dtype, trust_remote_code=True)
+        self.model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan-13B-Chat")
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)
         # ignoring parameters! Default to configs in generation_config.json.
         messages = [{"role": "user", "content": inputs}]
-        response = this.model.chat(this.tokenizer, messages)
+        response = self.model.chat(self.tokenizer, messages)
         return [{'generated_text': response}]