Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|beginoftext|>": 21134,
+  "<|endoftext|>": 21133
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "<|beginoftext|>",
+  "mask_token": "[MASK]",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<|beginoftext|>",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1024,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "<|endoftext|>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}