resize model when special tokenizer present

examples/run_lm_finetuning.py

@@ -215,6 +215,7 @@ def train(args, train_dataset, model, tokenizer):
 
     global_step = 0
     tr_loss, logging_loss = 0.0, 0.0
+    model.resize_token_embeddings(len(tokenizer))
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
     set_seed(args)  # Added here for reproducibility (even between python 2 and 3)