add tokenizer

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, "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, "lowercase": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/ff8c49f786a0eddfc4a865f09ab427d99cd22cd2c866230724f7b7133952dc1a.234ad2446e4daff2bd4ca6fa6a13d9d878b748e62b97f23af6e858fd5fc3dbec", "tokenizer_file": null, "name_or_path": "monsoon-nlp/bert-base-thai", "tokenizer_class": "BertTokenizer"}