Upload tokenizer

merges.txt

@@ -0,0 +1,41 @@
+#version: 0.2
+4 3
+3 2
+2 5
+3 3
+2 3
+2 0
+3 0
+1 4
+3 9
+1 3
+2 7
+2 2
+2 9
+1 5
+3 8
+1 6
+4 9
+4 8
+1 7
+3 4
+4 7
+4 2
+1 2
+4 5
+4 6
+3 7
+3 5
+1 8
+4 1
+4 0
+4 4
+2 8
+3 6
+2 4
+2 1
+2 6
+1 1
+1 9
+1 0
+3 1

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,217 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[BOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "[BOS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[EOS]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[BOS]": {
+        "id": "[BOS]",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "[BOS]"
+        ]
+      },
+      "[EOS]": {
+        "id": "[EOS]",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "[EOS]"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "[UNK]": 0,
+      "[BOS]": 1,
+      "[EOS]": 2,
+      "[PAD]": 3,
+      "0": 4,
+      "1": 5,
+      "2": 6,
+      "3": 7,
+      "4": 8,
+      "5": 9,
+      "6": 10,
+      "7": 11,
+      "8": 12,
+      "9": 13,
+      "43": 14,
+      "32": 15,
+      "25": 16,
+      "33": 17,
+      "23": 18,
+      "20": 19,
+      "30": 20,
+      "14": 21,
+      "39": 22,
+      "13": 23,
+      "27": 24,
+      "22": 25,
+      "29": 26,
+      "15": 27,
+      "38": 28,
+      "16": 29,
+      "49": 30,
+      "48": 31,
+      "17": 32,
+      "34": 33,
+      "47": 34,
+      "42": 35,
+      "12": 36,
+      "45": 37,
+      "46": 38,
+      "37": 39,
+      "35": 40,
+      "18": 41,
+      "41": 42,
+      "40": 43,
+      "44": 44,
+      "28": 45,
+      "36": 46,
+      "24": 47,
+      "21": 48,
+      "26": 49,
+      "11": 50,
+      "19": 51,
+      "10": 52,
+      "31": 53
+    },
+    "merges": [
+      "4 3",
+      "3 2",
+      "2 5",
+      "3 3",
+      "2 3",
+      "2 0",
+      "3 0",
+      "1 4",
+      "3 9",
+      "1 3",
+      "2 7",
+      "2 2",
+      "2 9",
+      "1 5",
+      "3 8",
+      "1 6",
+      "4 9",
+      "4 8",
+      "1 7",
+      "3 4",
+      "4 7",
+      "4 2",
+      "1 2",
+      "4 5",
+      "4 6",
+      "3 7",
+      "3 5",
+      "1 8",
+      "4 1",
+      "4 0",
+      "4 4",
+      "2 8",
+      "3 6",
+      "2 4",
+      "2 1",
+      "2 6",
+      "1 1",
+      "1 9",
+      "1 0",
+      "3 1"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[EOS]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "[UNK]"
+}

vocab.json

@@ -0,0 +1 @@
+{"[UNK]":0,"[BOS]":1,"[EOS]":2,"[PAD]":3,"0":4,"1":5,"2":6,"3":7,"4":8,"5":9,"6":10,"7":11,"8":12,"9":13,"43":14,"32":15,"25":16,"33":17,"23":18,"20":19,"30":20,"14":21,"39":22,"13":23,"27":24,"22":25,"29":26,"15":27,"38":28,"16":29,"49":30,"48":31,"17":32,"34":33,"47":34,"42":35,"12":36,"45":37,"46":38,"37":39,"35":40,"18":41,"41":42,"40":43,"44":44,"28":45,"36":46,"24":47,"21":48,"26":49,"11":50,"19":51,"10":52,"31":53}