add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"pad_token": "[PAD]", "mask_token": "[MASK]"}

tokenizer.json

@@ -0,0 +1,50 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Lowercase"
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "[MASK]": 0,
+      "[PAD]": 1,
+      "a": 2,
+      "c": 3,
+      "g": 4,
+      "t": 5
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"mask_token": "[MASK]", "pad_token": "[PAD]", "special_tokens_map_file": "../../data/mlm/tokenizer_bare/special_tokens_map.json", "name_or_path": "checkpoint-80000", "tokenizer_class": "PreTrainedTokenizerFast"}