update tokenizer with fast version

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

special_tokens_map.json

@@ -1 +1,19 @@
-{"bos_token": "[BOS]", "eos_token": "[EOS]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[UNC]", "[LEN]", "[LPP]", "[BEST2010]", "[LST20]", "[TNHC]", "[VISTEC-TPTH2021]", "[WS160]"]}
+{
+  "additional_special_tokens": [
+    "[UNC]",
+    "[LEN]",
+    "[LPP]",
+    "[BEST2010]",
+    "[LST20]",
+    "[TNHC]",
+    "[VISTEC-TPTH2021]",
+    "[WS160]"
+  ],
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ae015e8a33253054d75c1de67a95f78284233344b9ca628b84acf260fc68be
+size 33896546

tokenizer_config.json

@@ -1 +1,16 @@
-{"do_lower_case": false, "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": null, "special_tokens_map_file": null, "tokenizer_file": "data/ptm/bert-base-multilingual-cased/tokenizer.json", "name_or_path": "data/ptm/bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "from_slow": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "tmp/tokenizers/th/",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}