Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,73 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<PAD>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "<PAD>": 0,
+      "A": 1,
+      "R": 2,
+      "N": 3,
+      "D": 4,
+      "B": 5,
+      "C": 6,
+      "E": 7,
+      "Q": 8,
+      "Z": 9,
+      "G": 10,
+      "H": 11,
+      "I": 12,
+      "L": 13,
+      "K": 14,
+      "M": 15,
+      "F": 16,
+      "P": 17,
+      "S": 18,
+      "T": 19,
+      "W": 20,
+      "Y": 21,
+      "V": 22,
+      "1": 23,
+      "2": 24,
+      "3": 25
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 512,
+  "pad_token": "<PAD>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}