add tokenizer

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[BOS]": 30003,
+  "[BSEP]": 30001,
+  "[EOS]": 30004,
+  "[FSEP]": 30002,
+  "[SOB]": 30000
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "name_or_path": "/content/drive/MyDrive/CaMelBERTSharedtopic2Poem6",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "[UNK]"
+}