Update inference_server.py

inference_server.py

@@ -12,11 +12,14 @@ strings = set() # Set to store all input strings
 # Load the BERT LM and set it to eval mode
 model = transformers.BertModel.from_pretrained('bert-base-cased')
 model.eval()
+
+# Load the BERT tokenizer
+tokenizer = transformers.BertTokenizer.from_pretrained('bert-base-cased')
 def predict(input_text: str):
     # Add the new input string to the set of strings
     strings.add(input_text)
     # Convert the input strings to input tensors for the BERT LM
-    input_tensors = transformers.BertTokenizer.from_pretrained('bert-base-cased').batch_encode_plus(list(strings), max_length=512,
+    input_tensors = tokenizer.batch_encode_plus(list(strings), max_length=512,
                                                                                     pad_to_max_length=True, return_tensors='pt')
     input_ids = input_tensors['input_ids']