modify tokenizer config

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -1,5 +1 @@
-{
-  "do_lower_case": true,
-  "strip_accents": false,
-  "model_max_length": 512
-}
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": false, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null,}