Update tokenizer_config.json

The model max length is currently set at a value within the `transformers` toolkit directly, as can be seen here: https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert/tokenization_bert.py#L90-L91

We're removing these definition as legacy, we're therefore updating the remote checkpoints to ensure that this information is not lost. Thank you!

tokenizer_config.json

@@ -1,3 +1,4 @@
 {
-  "do_lower_case": true
+  "do_lower_case": true,
+  "model_max_length": 512
 }