Update handler.py

Moving device assignment to pipeline call

handler.py

@@ -10,14 +10,10 @@ dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.
 class EndpointHandler:
     def __init__(self, path=""):
         # load the model
-        tokenizer = AutoTokenizer.from_pretrained(path)
-        
-        config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
-        config.init_device = 'cuda:0'
-        
-        model = AutoModelForCausalLM.from_pretrained(path, config=config, device_map="auto", torch_dtype=dtype, trust_remote_code=True)
+        tokenizer = AutoTokenizer.from_pretrained(path)        
+        model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", torch_dtype=dtype, trust_remote_code=True)
         # create inference pipeline
-        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device='cuda:0')
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)