Update run.py for draft_target_model (NVIDIA#3615)

This change makes the draft target model works without mismatch in the vocab size

Signed-off-by: mayani-nv <[email protected]>
Co-authored-by: rakib-hasan <[email protected]>

Author: mayani-nv

examples/run.py

@@ -440,7 +440,7 @@ def main(args):
 
         outputs = run_dtm_pld(batch_input_ids, args, runtime_rank, end_id,
                               pad_id, stop_words_list, bad_words_list,
-                              tokenizer.vocab_size)
+                              len(tokenizer))
         if not args.streaming:  # Unpack runner from the return value in No-Streaming mode
             outputs, runner = list(outputs)[0]