Upload tokenizer

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<causal>": 50260,
+  "<fitm_result>": 50259,
+  "<fitm_start>": 50257,
+  "<mlm_end>": 50263,
+  "<mlm_start>": 50261,
+  "<multiple_tok_mask>": 50258,
+  "<single_tok_mask>": 50262
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "additional_special_tokens": [
+    "<fitm_start>",
+    "<multiple_tok_mask>",
+    "<fitm_result>",
+    "<causal>",
+    "<mlm_start>",
+    "<single_tok_mask>",
+    "<mlm_end>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}