add tokenizer config

README.md

@@ -0,0 +1,14 @@
+
+---
+language:
+- en
+thumbnail: https://raw.githubusercontent.com/JetRunner/BERT-of-Theseus/master/bert-of-theseus.png
+tags:
+- sequence
+- classification
+license: apache-2.0
+datasets:
+- imdb
+metrics:
+- accuracy
+---

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}