Update handler.py

handler.py

@@ -12,7 +12,7 @@ tokenizer.push_to_hub(repo_name="text-summary-gpt2-short", repo_id="Lin0He/text-
 import torch
 import numpy as np
 from typing import Dict, List, Any
-from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline, AutoModelForCausalLM, GPT2Tokenizer
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
@@ -72,7 +72,7 @@ def model_infer(model, tokenizer, review, max_length=300):
 class EndpointHandler():
     def __init__(self, path=""):
         # load model and tokenizer from path
-        self.tokenizer = AutoTokenizer.from_pretrained("Lin0He/text-summary-gpt2-short")
+        self.tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
         self.model = AutoModelForCausalLM.from_pretrained("Lin0He/text-summary-gpt2-short")