Added Deberta model type support (#34308)

* Added Deberta model type for 'add_prefix_space' functionality

* housekeeping

---------

Co-authored-by: Filippos Ventirozos <filippos.ventirozos@autotrader.co.uk>

examples/pytorch/token-classification/run_ner.py

@@ -366,7 +366,7 @@ def get_label_list(labels):
     )
 
     tokenizer_name_or_path = model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path
-    if config.model_type in {"bloom", "gpt2", "roberta"}:
+    if config.model_type in {"bloom", "gpt2", "roberta", "deberta"}:
         tokenizer = AutoTokenizer.from_pretrained(
             tokenizer_name_or_path,
             cache_dir=model_args.cache_dir,