Fix `model_max_length` in `tokenizer_config.json`

See https://huggingface.co/BAAI/bge-large-en/discussions/7 for more info.

tokenizer_config.json

@@ -4,7 +4,7 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",