add model_max_length

without specifying the model_max_length for the tokenizer defaults to a very large int, and inference crashes

I believe this may be due to a recent change to transformers - bert-large-uncased config was updated 2 months ago: https://huggingface.co/google-bert/bert-large-uncased/commit/6da4b6a26a1877e173fca3225479512db81a5e5b

tokenizer_config.json

@@ -1,3 +1 @@
-{
-  "do_lower_case": true
-}
+{"do_lower_case": true, "model_max_length": 512}