Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "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
+  },
+  "mask_token": {
+    "content": "([mask])",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "([pad])",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "▁",
+    "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 +1,4144 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "([bos])",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "([eos])",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "([unk])",
+      "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
+    },
+    {
+      "id": 4,
+      "content": "([mask])",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 8,
+      "content": "▁",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "([eos])",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "([eos])",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "([eos])",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "([bos])": {
+        "id": "([bos])",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "([bos])"
+        ]
+      },
+      "([eos])": {
+        "id": "([eos])",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "([eos])"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
+  },
+  "model": {
+    "type": "Unigram",
+    "unk_id": 2,
+    "vocab": [
+      [
+        "([bos])",
+        0.0
+      ],
+      [
+        "([eos])",
+        0.0
+      ],
+      [
+        "([unk])",
+        0.0
+      ],
+      [
+        "([pad])",
+        0.0
+      ],
+      [
+        "([mask])",
+        0.0
+      ],
+      [
+        "s",
+        -2.7142058517262875
+      ],
+      [
+        "▁the",
+        -3.266077726769307
+      ],
+      [
+        "t",
+        -3.4681844110225715
+      ],
+      [
+        "▁",
+        -3.5045292221545505
+      ],
+      [
+        "e",
+        -3.53243604604831
+      ],
+      [
+        "d",
+        -3.746795505406471
+      ],
+      [
+        "a",
+        -3.966644864782042
+      ],
+      [
+        "▁a",
+        -4.045297326782757
+      ],
+      [
+        "ed",
+        -4.078676075277873
+      ],
+      [
+        "i",
+        -4.082775869080045
+      ],
+      [
+        "n",
+        -4.092123175436564
+      ],
+      [
+        "r",
+        -4.168281078700067
+      ],
+      [
+        "▁of",
+        -4.267933495012722
+      ],
+      [
+        "▁in",
+        -4.327956814336762
+      ],
+      [
+        "l",
+        -4.346454994977579
+      ],
+      [
+        "▁to",
+        -4.542642082528419
+      ],
+      [
+        "y",
+        -4.547846816375564
+      ],
+      [
+        "▁is",
+        -4.561382632099523
+      ],
+      [
+        "o",
+        -4.564814277299618
+      ],
+      [
+        "ing",
+        -4.5768138723470955
+      ],
+      [
+        "▁and",
+        -4.582373336093488
+      ],
+      [
+        "▁was",
+        -4.767419810016145
+      ],
+      [
+        "m",
+        -4.94726376910474
+      ],
+      [
+        "▁he",
+        -4.974815241685285
+      ],
+      [
+        "c",
+        -5.022225255873906
+      ],
+      [
+        "er",
+        -5.036810038674725
+      ],
+      [
+        "p",
+        -5.060332470938388
+      ],
+      [
+        "b",
+        -5.068433510800604
+      ],
+      [
+        "in",
+        -5.15900035344338
+      ],
+      [
+        "ly",
+        -5.193847645206915
+      ],
+      [
+        "▁it",
+        -5.215618381775846
+      ],
+      [
+        "f",
+        -5.2711163831213685
+      ],
+      [
+        "al",
+        -5.301249758864202
+      ],
+      [
+        "or",
+        -5.312048292929285
+      ],
+      [
+        "▁be",
+        -5.3344236780927545
+      ],
+      [
+        "▁for",
+        -5.354847011896672
+      ],
+      [
+        "▁re",
+        -5.430822952843879
+      ],
+      [
+        "g",
+        -5.446659545835704
+      ],
+      [
+        "u",
+        -5.449209803829399
+      ],
+      [
+        "an",
+        -5.461456262180917
+      ],
+      [
+        "le",
+        -5.485306773836843
+      ],
+      [
+        "w",
+        -5.50802990965715
+      ],
+      [
+        "ar",
+        -5.523425129847167
+      ],
+      [
+        "re",
+        -5.564005312911405
+      ],
+      [
+        "▁are",
+        -5.585534202380469
+      ],
+      [
+        "h",
+        -5.6644928360782245
+      ],
+      [
+        "-",
+        -5.670696987962916
+      ],
+      [
+        "k",
+        -5.678877446917772
+      ],
+      [
+        "▁on",
+        -5.687817643627447
+      ],
+      [
+        "en",
+        -5.715569650173016
+      ],
+      [
+        "▁his",
+        -5.72049064645074
+      ],
+      [
+        "ic",
+        -5.732452984995662
+      ],
+      [
+        "▁by",
+        -5.73361521100181
+      ],
+      [
+        "on",
+        -5.745444310105055
+      ],
+      [
+        "▁with",
+        -5.745727056090052
+      ],
+      [
+        "▁this",
+        -5.7852743858084335
+      ],
+      [
+        "▁also",
+        -5.789222886415049
+      ],
+      [
+        "is",
+        -5.791623269794124
+      ],
+      [
+        "it",
+        -5.838030009896425
+      ],
+      [
+        "▁as",
+        -5.950372775660929
+      ],
+      [
+        "th",
+        -5.961565786912297
+      ],
+      [
+        "▁an",
+        -5.987225115194679
+      ],
+      [
+        "ch",
+        -6.00110634144939
+      ],
+      [
+        "ce",
+        -6.005579943200157
+      ],
+      [
+        "ation",
+        -6.016209515041735
+      ],
+      [
+        "▁de",
+        -6.024326469068459
+      ],
+      [
+        "▁were",
+        -6.120402098115683
+      ],
+      [
+        "ck",
+        -6.13570396348357
+      ],
+      [
+        "▁has",
+        -6.1604740749733615
+      ],
+      [
+        "▁at",
+        -6.1665615024086815
+      ],
+      [
+        "▁con",
+        -6.171395914280048
+      ],
+      [
+        "ter",
+        -6.178357796176943
+      ],
+      [
+        "▁pa",
+        -6.184579472989292
+      ],
+      [
+        "▁di",
+        -6.192506491397001
+      ],
+      [
+        "▁from",
+        -6.2274963476148155
+      ],
+      [
+        "z",
+        -6.233832656471341
+      ],
+      [
+        "▁that",
+        -6.259145222689275
+      ],
+      [
+        "▁she",
+        -6.261823071383178
+      ],
+      [
+        "ent",
+        -6.273559485076177
+      ],
+      [
+        "ve",
+        -6.287745527877524
+      ],
+      [
+        "ll",
+        -6.296934130149953
+      ],
+      [
+        "ion",
+        -6.303428379883117
+      ],
+      [
+        "ur",
+        -6.3407337786835125
+      ],
+      [
+        "▁not",
+        -6.346123894928427
+      ],
+      [
+        "▁ro",
+        -6.378132550002775
+      ],
+      [
+        "▁me",
+        -6.3892165501912395
+      ],
+      [
+        "us",
+        -6.393408207350147
+      ],
+      [
+        "ate",
+        -6.404987541552584
+      ],
+      [
+        "ge",
+        -6.407969713535913
+      ],
+      [
+        "▁se",
+        -6.417440557255812
+      ],
+      [
+        "▁c",
+        -6.428010656832997
+      ],
+      [
+        "x",
+        -6.428867114215537
+      ],
+      [
+        "ment",
+        -6.4427680144962345
+      ],
+      [
+        "est",
+        -6.442833858954188
+      ],
+      [
+        "▁i",
+        -6.4466213063191145
+      ],
+      [
+        "v",
+        -6.4606981545382105
+      ],
+      [
+        "▁ho",
+        -6.4783104949578245
+      ],
+      [
+        "▁ma",
+        -6.498125017152299
+      ],
+      [
+        "▁do",
+        -6.501752446265398
+      ],
+      [
+        "▁her",
+        -6.515398164184424
+      ],
+      [
+        "▁bo",
+        -6.522430744871071
+      ],
+      [
+        "im",
+        -6.53403598402163
+      ],
+      [
+        "▁no",
+        -6.534558554272426
+      ],
+      [
+        "▁have",
+        -6.5685136086251585
+      ],
+      [
+        "▁two",
+        -6.575123668331273
+      ],
+      [
+        "▁co",
+        -6.591894918105922
+      ],
+      [
+        "▁k",
+        -6.606856421143078
+      ],
+      [
+        "ver",
+        -6.607525875982011
+      ],
+      [
+        "▁fa",
+        -6.613660208245481
+      ],
+      [
+        "▁ba",
+        -6.615313155284893
+      ],
+      [
+        "at",
+        -6.625740611824233
+      ],
+      [
+        "▁ex",
+        -6.62637779295275
+      ],
+      [
+        "▁ra",
+        -6.628800941363236
+      ],
+      [
+        "ry",
+        -6.653214733681473
+      ],
+      [
+        "▁all",
+        -6.66469564745948
+      ],
+      [
+        "▁there",
+        -6.66844118808865
+      ],
+      [
+        "▁mo",
+        -6.67106236533283
+      ],
+      [
+        "am",
+        -6.676242636979339
+      ],
+      [
+        "▁they",
+        -6.677178799395
+      ],
+      [
+        "▁one",
+        -6.677384225117864
+      ],
+      [
+        "▁can",
+        -6.681420059563639
+      ],
+      [
+        "vi",
+        -6.709959752152264
+      ],
+      [
+        "lo",
+        -6.713154281118065
+      ],
+      [
+        "ow",
+        -6.723831218437194
+      ],
+      [
+        "▁fi",
+        -6.726589216495869
+      ],
+      [
+        "▁pro",
+        -6.7314450012561
+      ],
+      [
+        "▁ha",
+        -6.749209503748762
+      ],
+      [
+        "▁ch",
+        -6.772095921880828
+      ],
+      [
+        "▁or",
+        -6.776365650103081
+      ],
+      [
+        "▁sp",
+        -6.786393276062583
+      ],
+      [
+        "▁had",
+        -6.79223049765579
+      ],
+      [
+        "▁la",
+        -6.795382351097437
+      ],
+      [
+        "ke",
+        -6.800168033699109
+      ],
+      [
+        "▁su",
+        -6.800774748957359
+      ],
+      [
+        "ies",
+        -6.810016118434552
+      ],
+      [
+        "ers",
+        -6.812082064826704
+      ],
+      [
+        "ive",
+        -6.81569606544878
+      ],
+      [
+        "▁mi",
+        -6.821300864111514
+      ],
+      [
+        "▁lo",
+        -6.825339535971379
+      ],
+      [
+        "ated",
+        -6.825595609411938
+      ],
+      [
+        "ian",
+        -6.8258488952010925
+      ],
+      [
+        "me",
+        -6.827060831018173
+      ],
+      [
+        "▁part",
+        -6.831319323934572
+      ],
+      [
+        "▁un",
+        -6.834647079614271
+      ],
+      [
+        "▁so",
+        -6.840942547772675
+      ],
+      [
+        "tion",
+        -6.845914749541093
+      ],
+      [
+        "▁after",
+        -6.84985564767894
+      ],
+      [
+        "▁po",
+        -6.857737040629791
+      ],
+      [
+        "▁been",
+        -6.859188228545115
+      ],
+      [
+        "▁first",
+        -6.861598581896203
+      ],
+      [
+        "tic",
+        -6.878762521429671
+      ],
+      [
+        "om",
+        -6.883129570248538
+      ],
+      [
+        "▁new",
+        -6.896230592082377
+      ],
+      [
+        "▁school",
+        -6.905097652791072
+      ],
+      [
+        "um",
+        -6.9090275544645525
+      ],
+      [
+        "▁their",
+        -6.912734101387549
+      ],
+      [
+        "▁sc",
+        -6.933326754224046
+      ],
+      [
+        "▁its",
+        -6.937682807122778
+      ],
+      [
+        "▁le",
+        -6.940358887201773
+      ],
+      [
+        "▁w",
+        -6.940842423851915
+      ],
+      [
+        "ul",
+        -6.94110827313745
+      ],
+      [
+        "▁work",
+        -6.949677715478737
+      ],
+      [
+        "▁other",
+        -6.9523598336439125
+      ],
+      [
+        "▁we",
+        -6.95346715825179
+      ],
+      [
+        "ut",
+        -6.960916166059883
+      ],
+      [
+        "man",
+        -6.964884341526368
+      ],
+      [
+        "▁some",
+        -6.977696078158498
+      ],
+      [
+        "un",
+        -6.979877324440615
+      ],
+      [
+        "▁time",
+        -6.986570441870228
+      ],
+      [
+        "▁ca",
+        -6.988490157320621
+      ],
+      [
+        "▁you",
+        -6.99639882428054
+      ],
+      [
+        "ance",
+        -6.999274442223426
+      ],
+      [
+        "▁play",
+        -7.002502888833199
+      ],
+      [
+        "▁go",
+        -7.004466016906287
+      ],
+      [
+        "▁li",
+        -7.007368121818985
+      ],
+      [
+        "ity",
+        -7.021854561852786
+      ],
+      [
+        "ng",
+        -7.043741300457798
+      ],
+      [
+        "ton",
+        -7.044389861055102
+      ],
+      [
+        "ard",
+        -7.052742092697903
+      ],
+      [
+        "ma",
+        -7.053038033509955
+      ],
+      [
+        "op",
+        -7.0555392015014196
+      ],
+      [
+        "▁com",
+        -7.060523474132848
+      ],
+      [
+        "▁sta",
+        -7.072938466920112
+      ],
+      [
+        "▁fl",
+        -7.093443929951222
+      ],
+      [
+        "▁bi",
+        -7.094392877971398
+      ],
+      [
+        "mp",
+        -7.100070525723389
+      ],
+      [
+        "▁these",
+        -7.105941098155345
+      ],
+      [
+        "▁but",
+        -7.106296726596112
+      ],
+      [
+        "vo",
+        -7.1077544081210995
+      ],
+      [
+        "ide",
+        -7.108633982065594
+      ],
+      [
+        "▁car",
+        -7.1088530750515595
+      ],
+      [
+        "▁up",
+        -7.109501518373792
+      ],
+      [
+        "age",
+        -7.114556836092426
+      ],
+      [
+        "if",
+        -7.118715610465305
+      ],
+      [
+        "▁pre",
+        -7.126244139579125
+      ],
+      [
+        "ence",
+        -7.141668416831232
+      ],
+      [
+        "▁most",
+        -7.145628418047821
+      ],
+      [
+        "▁later",
+        -7.151336704475602
+      ],
+      [
+        "▁cl",
+        -7.151458790940525
+      ],
+      [
+        "ber",
+        -7.156518168649448
+      ],
+      [
+        "co",
+        -7.171591273376702
+      ],
+      [
+        "▁many",
+        -7.173579097459429
+      ],
+      [
+        "▁th",
+        -7.176175909519051
+      ],
+      [
+        "▁comp",
+        -7.177138295798342
+      ],
+      [
+        "▁bu",
+        -7.179756301325936
+      ],
+      [
+        "▁pi",
+        -7.187954413412804
+      ],
+      [
+        "ell",
+        -7.188247059066965
+      ],
+      [
+        "per",
+        -7.200276230714959
+      ],
+      [
+        "able",
+        -7.200683922295507
+      ],
+      [
+        "▁him",
+        -7.20131847471121
+      ],
+      [
+        "▁mar",
+        -7.212074763797912
+      ],
+      [
+        "lu",
+        -7.2142484300898495
+      ],
+      [
+        "▁sh",
+        -7.22127923539019
+      ],
+      [
+        "ight",
+        -7.222925534341611
+      ],
+      [
+        "▁ne",
+        -7.225806940112452
+      ],
+      [
+        "▁fr",
+        -7.226512915547989
+      ],
+      [
+        "▁three",
+        -7.231230878985501
+      ],
+      [
+        "▁used",
+        -7.232260532757048
+      ],
+      [
+        "▁town",
+        -7.232309625465101
+      ],
+      [
+        "came",
+        -7.242967594407505
+      ],
+      [
+        "▁vi",
+        -7.249586832921494
+      ],
+      [
+        "ction",
+        -7.267841526514102
+      ],
+      [
+        "▁high",
+        -7.268061510704944
+      ],
+      [
+        "ous",
+        -7.272224039471849
+      ],
+      [
+        "pp",
+        -7.284848779885527
+      ],
+      [
+        "▁sto",
+        -7.286863027829197
+      ],
+      [
+        "▁however",
+        -7.290660280376883
+      ],
+      [
+        "j",
+        -7.292167342606396
+      ],
+      [
+        "▁fe",
+        -7.29321968286089
+      ],
+      [
+        "land",
+        -7.297367552397095
+      ],
+      [
+        "▁name",
+        -7.2993152341360386
+      ],
+      [
+        "ture",
+        -7.307785305845888
+      ],
+      [
+        "pe",
+        -7.312139567814976
+      ],
+      [
+        "▁ri",
+        -7.323717065692481
+      ],
+      [
+        "▁form",
+        -7.324580994154152
+      ],
+      [
+        "nes",
+        -7.326451748233499
+      ],
+      [
+        "▁ja",
+        -7.328301983192173
+      ],
+      [
+        "ph",
+        -7.337800488161985
+      ],
+      [
+        "▁city",
+        -7.33840895360021
+      ],
+      [
+        "ship",
+        -7.3426208721170045
+      ],
+      [
+        "he",
+        -7.345670806055956
+      ],
+      [
+        "▁va",
+        -7.360810729787437
+      ],
+      [
+        "▁out",
+        -7.363565673300144
+      ],
+      [
+        "▁man",
+        -7.36968256429466
+      ],
+      [
+        "▁state",
+        -7.370327378767264
+      ],
+      [
+        "▁known",
+        -7.370440976732693
+      ],
+      [
+        "port",
+        -7.377756610728268
+      ],
+      [
+        "▁pri",
+        -7.381388302138948
+      ],
+      [
+        "▁gra",
+        -7.383177000548869
+      ],
+      [
+        "ok",
+        -7.383733453838447
+      ],
+      [
+        "▁only",
+        -7.387883335459335
+      ],
+      [
+        "▁col",
+        -7.389262632768462
+      ],
+      [
+        "bo",
+        -7.391109581748884
+      ],
+      [
+        "ical",
+        -7.391580499253513
+      ],
+      [
+        "▁pe",
+        -7.399934877502478
+      ],
+      [
+        "ally",
+        -7.403084708646189
+      ],
+      [
+        "ary",
+        -7.409070412401109
+      ],
+      [
+        "▁over",
+        -7.410534307555428
+      ],
+      [
+        "▁into",
+        -7.410869636527392
+      ],
+      [
+        "ward",
+        -7.419884239492999
+      ],
+      [
+        "▁jo",
+        -7.422160557714333
+      ],
+      [
+        "▁born",
+        -7.430518002046895
+      ],
+      [
+        "▁ga",
+        -7.4335458543965505
+      ],
+      [
+        "▁both",
+        -7.440386115770842
+      ],
+      [
+        "ak",
+        -7.440912383296125
+      ],
+      [
+        "▁wa",
+        -7.444403483510561
+      ],
+      [
+        "▁du",
+        -7.446048536615738
+      ],
+      [
+        "way",
+        -7.450531353727385
+      ],
+      [
+        "ha",
+        -7.451093620092589
+      ],
+      [
+        "min",
+        -7.454793299015211
+      ],
+      [
+        "▁more",
+        -7.46025359771626
+      ],
+      [
+        "▁several",
+        -7.46155351166745
+      ],
+      [
+        "▁may",
+        -7.464386638009014
+      ],
+      [
+        "hi",
+        -7.474873473347444
+      ],
+      [
+        "ach",
+        -7.475967863371558
+      ],
+      [
+        "rie",
+        -7.477430846651114
+      ],
+      [
+        "during",
+        -7.483543807935675
+      ],
+      [
+        "po",
+        -7.488797793905288
+      ],
+      [
+        "to",
+        -7.496399356028629
+      ],
+      [
+        "▁pu",
+        -7.5024247527994845
+      ],
+      [
+        "ition",
+        -7.508572515264678
+      ],
+      [
+        "▁hu",
+        -7.520178891659468
+      ],
+      [
+        "▁call",
+        -7.522546979699779
+      ],
+      [
+        "tro",
+        -7.522743830761915
+      ],
+      [
+        "▁gu",
+        -7.527180358766337
+      ],
+      [
+        "our",
+        -7.527871548238945
+      ],
+      [
+        "▁fo",
+        -7.528734746099595
+      ],
+      [
+        "▁tra",
+        -7.529798113254973
+      ],
+      [
+        "ill",
+        -7.539663319729819
+      ],
+      [
+        "▁war",
+        -7.543107348366025
+      ],
+      [
+        "▁inter",
+        -7.547998188062019
+      ],
+      [
+        "ven",
+        -7.549776682012061
+      ],
+      [
+        "▁through",
+        -7.5509209826877886
+      ],
+      [
+        "▁str",
+        -7.55303390521674
+      ],
+      [
+        "▁area",
+        -7.55309930449728
+      ],
+      [
+        "▁four",
+        -7.5683042519954675
+      ],
+      [
+        "ther",
+        -7.581144427874319
+      ],
+      [
+        "ru",
+        -7.581598878357532
+      ],
+      [
+        "ple",
+        -7.582206344601326
+      ],
+      [
+        "ctor",
+        -7.586640802884986
+      ],
+      [
+        "▁include",
+        -7.591817594156
+      ],
+      [
+        "gan",
+        -7.593009037635843
+      ],
+      [
+        "ial",
+        -7.598363567842016
+      ],
+      [
+        "▁mon",
+        -7.600514066692368
+      ],
+      [
+        "▁found",
+        -7.603177806136431
+      ],
+      [
+        "▁large",
+        -7.60425817554837
+      ],
+      [
+        "▁named",
+        -7.604349942408133
+      ],
+      [
+        "▁film",
+        -7.6107690769879905
+      ],
+      [
+        "one",
+        -7.61168663886918
+      ],
+      [
+        "▁year",
+        -7.613135706422803
+      ],
+      [
+        "cu",
+        -7.61464770866718
+      ],
+      [
+        "▁now",
+        -7.616560120776802
+      ],
+      [
+        "▁main",
+        -7.61875403518334
+      ],
+      [
+        "▁act",
+        -7.619545833972056
+      ],
+      [
+        "▁years",
+        -7.624174493258776
+      ],
+      [
+        "▁under",
+        -7.624641070551563
+      ],
+      [
+        "pla",
+        -7.625342385687491
+      ],
+      [
+        "▁would",
+        -7.62591928350338
+      ],
+      [
+        "▁el",
+        -7.630239688073948
+      ],
+      [
+        "ugh",
+        -7.63104379582024
+      ],
+      [
+        "▁who",
+        -7.637430689406164
+      ],
+      [
+        "▁located",
+        -7.639639663232568
+      ],
+      [
+        "▁ph",
+        -7.641148172672809
+      ],
+      [
+        "qui",
+        -7.650555147784075
+      ],
+      [
+        "▁serve",
+        -7.65118037425113
+      ],
+      [
+        "all",
+        -7.6521999555041855
+      ],
+      [
+        "▁win",
+        -7.657514747870474
+      ],
+      [
+        "out",
+        -7.6620727172990755
+      ],
+      [
+        "▁mu",
+        -7.664262314551301
+      ],
+      [
+        "tra",
+        -7.667073786989784
+      ],
+      [
+        "▁county",
+        -7.678663322169475
+      ],
+      [
+        "ca",
+        -7.678784928209904
+      ],
+      [
+        "▁music",
+        -7.680205798060246
+      ],
+      [
+        "▁member",
+        -7.692517295429374
+      ],
+      [
+        "▁made",
+        -7.692683846728654
+      ],
+      [
+        "▁north",
+        -7.694848927655169
+      ],
+      [
+        "▁ar",
+        -7.695077464636402
+      ],
+      [
+        "▁will",
+        -7.695222090086128
+      ],
+      [
+        "qu",
+        -7.696477395104409
+      ],
+      [
+        "go",
+        -7.699125877208473
+      ],
+      [
+        "▁ju",
+        -7.700622245285146
+      ],
+      [
+        "ative",
+        -7.708442943572338
+      ],
+      [
+        "▁game",
+        -7.714260299934315
+      ],
+      [
+        "▁use",
+        -7.716268759613657
+      ],
+      [
+        "gre",
+        -7.720342078939407
+      ],
+      [
+        "▁south",
+        -7.723597548734455
+      ],
+      [
+        "▁when",
+        -7.724457878007165
+      ],
+      [
+        "gu",
+        -7.725111675361427
+      ],
+      [
+        "ten",
+        -7.728062513332755
+      ],
+      [
+        "▁cu",
+        -7.728757750547128
+      ],
+      [
+        "▁al",
+        -7.731282364559847
+      ],
+      [
+        "▁ru",
+        -7.732636285594861
+      ],
+      [
+        "▁show",
+        -7.734248770118976
+      ],
+      [
+        "▁well",
+        -7.735752980173226
+      ],
+      [
+        "be",
+        -7.73751916529182
+      ],
+      [
+        "que",
+        -7.738416211365767
+      ],
+      [
+        "▁team",
+        -7.744906600273033
+      ],
+      [
+        "▁dec",
+        -7.748590114307557
+      ],
+      [
+        "day",
+        -7.74882057412148
+      ],
+      [
+        "▁live",
+        -7.748841562549558
+      ],
+      [
+        "▁current",
+        -7.749386319744714
+      ],
+      [
+        "▁air",
+        -7.75356733439653
+      ],
+      [
+        "▁song",
+        -7.7575649653318735
+      ],
+      [
+        "▁har",
+        -7.761972061922897
+      ],
+      [
+        "ress",
+        -7.772706521497685
+      ],
+      [
+        "oun",
+        -7.791993882997721
+      ],
+      [
+        "▁end",
+        -7.803556018187734
+      ],
+      [
+        "▁own",
+        -7.810327499800259
+      ],
+      [
+        "▁second",
+        -7.81036139262782
+      ],
+      [
+        "▁long",
+        -7.811157169901499
+      ],
+      [
+        "▁university",
+        -7.812629058127959
+      ],
+      [
+        "▁each",
+        -7.812770346883285
+      ],
+      [
+        "▁people",
+        -7.815571820829902
+      ],
+      [
+        "va",
+        -7.8171224345984704
+      ],
+      [
+        "▁home",
+        -7.818243173720811
+      ],
+      [
+        "▁even",
+        -7.822899150287331
+      ],
+      [
+        "▁near",
+        -7.824766043743408
+      ],
+      [
+        "▁min",
+        -7.833999813522732
+      ],
+      [
+        "▁river",
+        -7.834066727973509
+      ],
+      [
+        "▁album",
+        -7.837144264030833
+      ],
+      [
+        "ner",
+        -7.838310941304613
+      ],
+      [
+        "▁day",
+        -7.838746787913525
+      ],
+      [
+        "▁group",
+        -7.840625948665041
+      ],
+      [
+        "▁tri",
+        -7.845782930179498
+      ],
+      [
+        "▁which",
+        -7.849184674718163
+      ],
+      [
+        "▁very",
+        -7.850118610783806
+      ],
+      [
+        "▁per",
+        -7.852578679917762
+      ],
+      [
+        "▁wi",
+        -7.853345192905438
+      ],
+      [
+        "▁see",
+        -7.854971386721919
+      ],
+      [
+        "▁park",
+        -7.857440569058344
+      ],
+      [
+        "▁remain",
+        -7.866258053049524
+      ],
+      [
+        "▁record",
+        -7.86627372801072
+      ],
+      [
+        "▁plan",
+        -7.867441977404482
+      ],
+      [
+        "▁house",
+        -7.868384538761825
+      ],
+      [
+        "▁cor",
+        -7.8690842103517795
+      ],
+      [
+        "▁cri",
+        -7.869966029419304
+      ],
+      [
+        "ful",
+        -7.872401132052909
+      ],
+      [
+        "▁about",
+        -7.872527635246447
+      ],
+      [
+        "ster",
+        -7.879474628954275
+      ],
+      [
+        "▁hi",
+        -7.8913198820025325
+      ],
+      [
+        "▁ste",
+        -7.891902564264035
+      ],
+      [
+        "▁app",
+        -7.8959806318621535
+      ],
+      [
+        "▁my",
+        -7.902911203934684
+      ],
+      [
+        "▁station",
+        -7.904737946816722
+      ],
+      [
+        "▁trans",
+        -7.905549996358863
+      ],
+      [
+        "▁appear",
+        -7.905789255454087
+      ],
+      [
+        "▁sha",
+        -7.908394538493971
+      ],
+      [
+        "▁fu",
+        -7.909972583185715
+      ],
+      [
+        "▁book",
+        -7.919587941740479
+      ],
+      [
+        "▁number",
+        -7.929104774203541
+      ],
+      [
+        "ron",
+        -7.929257022449795
+      ],
+      [
+        "▁son",
+        -7.931369450893685
+      ],
+      [
+        "▁children",
+        -7.93208047066055
+      ],
+      [
+        "▁bro",
+        -7.933468895640061
+      ],
+      [
+        "▁bra",
+        -7.934700751675502
+      ],
+      [
+        "iv",
+        -7.938760029010922
+      ],
+      [
+        "▁cha",
+        -7.942966567001887
+      ],
+      [
+        "▁did",
+        -7.9447807689970915
+      ],
+      [
+        "▁bar",
+        -7.948634641168312
+      ],
+      [
+        "▁small",
+        -7.951649323586803
+      ],
+      [
+        "▁place",
+        -7.951859486875602
+      ],
+      [
+        "▁family",
+        -7.961935579041397
+      ],
+      [
+        "▁world",
+        -7.966852400342038
+      ],
+      [
+        "▁than",
+        -7.9681738141577565
+      ],
+      [
+        "self",
+        -7.970459138366637
+      ],
+      [
+        "▁take",
+        -7.97161872996911
+      ],
+      [
+        "lie",
+        -7.973214071415059
+      ],
+      [
+        "▁cro",
+        -7.978140550768563
+      ],
+      [
+        "ign",
+        -7.984701206372987
+      ],
+      [
+        "mon",
+        -7.989075509554981
+      ],
+      [
+        "gg",
+        -7.995481614682102
+      ],
+      [
+        "▁je",
+        -7.995540895433944
+      ],
+      [
+        "▁public",
+        -7.998807429280355
+      ],
+      [
+        "▁still",
+        -8.003224829407744
+      ],
+      [
+        "▁what",
+        -8.003618611373797
+      ],
+      [
+        "▁old",
+        -8.005357733122956
+      ],
+      [
+        "▁back",
+        -8.00539355470375
+      ],
+      [
+        "▁local",
+        -8.007126538735287
+      ],
+      [
+        "▁sub",
+        -8.007150555042902
+      ],
+      [
+        "▁char",
+        -8.011578646920904
+      ],
+      [
+        "▁national",
+        -8.012226766921831
+      ],
+      [
+        "field",
+        -8.013402900265072
+      ],
+      [
+        "▁water",
+        -8.013649433342353
+      ],
+      [
+        "▁bri",
+        -8.014045011876082
+      ],
+      [
+        "cent",
+        -8.014160586092588
+      ],
+      [
+        "’",
+        -8.015973953544513
+      ],
+      [
+        "ail",
+        -8.017463589114351
+      ],
+      [
+        "▁like",
+        -8.018145510920542
+      ],
+      [
+        "▁same",
+        -8.026535720563228
+      ],
+      [
+        "▁move",
+        -8.028679732272929
+      ],
+      [
+        "▁often",
+        -8.031925541745231
+      ],
+      [
+        "▁east",
+        -8.032224176872553
+      ],
+      [
+        "▁line",
+        -8.038135161354873
+      ],
+      [
+        "▁village",
+        -8.04567103194289
+      ],
+      [
+        "▁college",
+        -8.046503238925455
+      ],
+      [
+        "▁general",
+        -8.049047221260539
+      ],
+      [
+        "▁release",
+        -8.057666862659708
+      ],
+      [
+        "ual",
+        -8.05941560872936
+      ],
+      [
+        "▁feature",
+        -8.060777601284805
+      ],
+      [
+        "air",
+        -8.06469528557162
+      ],
+      [
+        "bu",
+        -8.06559978520282
+      ],
+      [
+        "▁run",
+        -8.066118548954575
+      ],
+      [
+        "▁life",
+        -8.067827703226232
+      ],
+      [
+        "▁acc",
+        -8.067954466208333
+      ],
+      [
+        "▁tre",
+        -8.070026265483335
+      ],
+      [
+        "produc",
+        -8.076514847803574
+      ],
+      [
+        "▁said",
+        -8.079701979923772
+      ],
+      [
+        "▁service",
+        -8.081143377406775
+      ],
+      [
+        "▁develop",
+        -8.083908661159038
+      ],
+      [
+        "▁original",
+        -8.084503416909131
+      ],
+      [
+        "stan",
+        -8.086469325755983
+      ],
+      [
+        "▁any",
+        -8.098200211461617
+      ],
+      [
+        "▁band",
+        -8.098327335388335
+      ],
+      [
+        "▁perform",
+        -8.098499578240057
+      ],
+      [
+        "▁system",
+        -8.102831580476256
+      ],
+      [
+        "▁district",
+        -8.10761890136164
+      ],
+      [
+        "▁san",
+        -8.108768399104418
+      ],
+      [
+        "▁imp",
+        -8.10929873416065
+      ],
+      [
+        "ities",
+        -8.111638002998978
+      ],
+      [
+        "ches",
+        -8.11285125361874
+      ],
+      [
+        "▁design",
+        -8.116789280836645
+      ],
+      [
+        "▁produce",
+        -8.119375454629434
+      ],
+      [
+        "▁receive",
+        -8.120231190404635
+      ],
+      [
+        "▁building",
+        -8.121898666632525
+      ],
+      [
+        "▁never",
+        -8.126545002135302
+      ],
+      [
+        "ger",
+        -8.130115204245762
+      ],
+      [
+        "▁great",
+        -8.134791142183838
+      ],
+      [
+        "▁young",
+        -8.136855738522952
+      ],
+      [
+        "▁such",
+        -8.138350225328386
+      ],
+      [
+        "wood",
+        -8.13841345163245
+      ],
+      [
+        "ator",
+        -8.140989533059026
+      ],
+      [
+        "▁major",
+        -8.145423610039318
+      ],
+      [
+        "▁down",
+        -8.146806623553081
+      ],
+      [
+        "▁west",
+        -8.147961327620411
+      ],
+      [
+        "cul",
+        -8.157830988907978
+      ],
+      [
+        "ism",
+        -8.158572438822933
+      ],
+      [
+        "▁ten",
+        -8.159322922615742
+      ],
+      [
+        "▁continue",
+        -8.160241541603602
+      ],
+      [
+        "▁open",
+        -8.160628359147328
+      ],
+      [
+        "▁before",
+        -8.161405545705835
+      ],
+      [
+        "▁john",
+        -8.164968593843906
+      ],
+      [
+        "▁mean",
+        -8.168970507760951
+      ],
+      [
+        "▁ki",
+        -8.17127377427151
+      ],
+      [
+        "▁won",
+        -8.173306266378523
+      ],
+      [
+        "cause",
+        -8.175055296509452
+      ],
+      [
+        "▁common",
+        -8.176677746872262
+      ],
+      [
+        "▁list",
+        -8.178624124918302
+      ],
+      [
+        "▁church",
+        -8.179415838121052
+      ],
+      [
+        "▁term",
+        -8.182013213445382
+      ],
+      [
+        "▁different",
+        -8.184204788104076
+      ],
+      [
+        "▁consider",
+        -8.1851563338407
+      ],
+      [
+        "▁five",
+        -8.196664391335384
+      ],
+      [
+        "▁company",
+        -8.196896682724828
+      ],
+      [
+        "▁lead",
+        -8.200721273934157
+      ],
+      [
+        "▁return",
+        -8.203718862552664
+      ],
+      [
+        "▁following",
+        -8.207902699370319
+      ],
+      [
+        "▁married",
+        -8.209051623603013
+      ],
+      [
+        "▁bre",
+        -8.210483287529804
+      ],
+      [
+        "▁between",
+        -8.210691903680361
+      ],
+      [
+        "▁tu",
+        -8.213462772326872
+      ],
+      [
+        "▁rec",
+        -8.215463926545171
+      ],
+      [
+        "▁gen",
+        -8.215917728114515
+      ],
+      [
+        "ham",
+        -8.216969035771678
+      ],
+      [
+        "▁short",
+        -8.217254141523233
+      ],
+      [
+        "oli",
+        -8.225614503442134
+      ],
+      [
+        "▁father",
+        -8.22848236716985
+      ],
+      [
+        "▁law",
+        -8.228647185217952
+      ],
+      [
+        "▁arm",
+        -8.229279277171369
+      ],
+      [
+        "▁six",
+        -8.231654543783572
+      ],
+      [
+        "▁stand",
+        -8.232833790933514
+      ],
+      [
+        "▁island",
+        -8.23295114550086
+      ],
+      [
+        "▁office",
+        -8.238200655391111
+      ],
+      [
+        "▁while",
+        -8.244641901510835
+      ],
+      [
+        "less",
+        -8.248924390600386
+      ],
+      [
+        "▁disc",
+        -8.256617994514315
+      ],
+      [
+        "nish",
+        -8.259199372621973
+      ],
+      [
+        "gra",
+        -8.260633621736485
+      ],
+      [
+        "▁black",
+        -8.260770647781088
+      ],
+      [
+        "▁white",
+        -8.261792308266608
+      ],
+      [
+        "▁dra",
+        -8.262200199231897
+      ],
+      [
+        "ney",
+        -8.263411110832958
+      ],
+      [
+        "▁sk",
+        -8.265500405965897
+      ],
+      [
+        "▁another",
+        -8.265674793319524
+      ],
+      [
+        "▁series",
+        -8.266294741377507
+      ],
+      [
+        "▁club",
+        -8.267002341514132
+      ],
+      [
+        "▁last",
+        -8.269236209393974
+      ],
+      [
+        "▁just",
+        -8.273349054761749
+      ],
+      [
+        "▁every",
+        -8.278006948910186
+      ],
+      [
+        "com",
+        -8.280018321637833
+      ],
+      [
+        "▁season",
+        -8.288115490272684
+      ],
+      [
+        "▁port",
+        -8.290733597489803
+      ],
+      [
+        "▁where",
+        -8.295184730987494
+      ],
+      [
+        "▁qua",
+        -8.296429350369845
+      ],
+      [
+        "▁give",
+        -8.299217726872731
+      ],
+      [
+        "▁change",
+        -8.308720458584265
+      ],
+      [
+        "▁make",
+        -8.313624648627616
+      ],
+      [
+        "▁success",
+        -8.313757975103245
+      ],
+      [
+        "▁head",
+        -8.31419639704875
+      ],
+      [
+        "val",
+        -8.315678259685662
+      ],
+      [
+        "▁creat",
+        -8.31584048827423
+      ],
+      [
+        "▁support",
+        -8.321849696327526
+      ],
+      [
+        "▁could",
+        -8.322515152783604
+      ],
+      [
+        "▁seat",
+        -8.32640134292371
+      ],
+      [
+        "▁train",
+        -8.330865992183835
+      ],
+      [
+        "▁road",
+        -8.331399184562759
+      ],
+      [
+        "▁point",
+        -8.334421095707848
+      ],
+      [
+        "▁result",
+        -8.336023620788348
+      ],
+      [
+        "▁class",
+        -8.340924837616088
+      ],
+      [
+        "▁united",
+        -8.348404927787627
+      ],
+      [
+        "▁attend",
+        -8.360275666972496
+      ],
+      [
+        "▁provide",
+        -8.363626658034661
+      ],
+      [
+        "▁left",
+        -8.366263886762164
+      ],
+      [
+        "▁region",
+        -8.368167962944623
+      ],
+      [
+        "▁much",
+        -8.368402208046183
+      ],
+      [
+        "▁since",
+        -8.368429053605361
+      ],
+      [
+        "▁program",
+        -8.374836424335937
+      ],
+      [
+        "▁side",
+        -8.376583200926818
+      ],
+      [
+        "▁york",
+        -8.380279040621806
+      ],
+      [
+        "▁close",
+        -8.380373085198691
+      ],
+      [
+        "▁community",
+        -8.390043406624867
+      ],
+      [
+        "▁lake",
+        -8.392204961484412
+      ],
+      [
+        "���hand",
+        -8.396433663089894
+      ],
+      [
+        "mission",
+        -8.401877281679974
+      ],
+      [
+        "▁saint",
+        -8.402298456733927
+      ],
+      [
+        "▁brother",
+        -8.404312226238739
+      ],
+      [
+        "▁early",
+        -8.407057265507136
+      ],
+      [
+        "ug",
+        -8.419115623966269
+      ],
+      [
+        "▁single",
+        -8.421887011591389
+      ],
+      [
+        "▁popular",
+        -8.423581002353854
+      ],
+      [
+        "▁ka",
+        -8.425682083968539
+      ],
+      [
+        "▁government",
+        -8.431993278395476
+      ],
+      [
+        "▁refer",
+        -8.432759908155642
+      ],
+      [
+        "▁good",
+        -8.434851815345286
+      ],
+      [
+        "ized",
+        -8.436194795790644
+      ],
+      [
+        "ground",
+        -8.438060934245975
+      ],
+      [
+        "nder",
+        -8.44084331443392
+      ],
+      [
+        "▁final",
+        -8.441099307688706
+      ],
+      [
+        "▁german",
+        -8.446351868468698
+      ],
+      [
+        "▁publish",
+        -8.44811269015751
+      ],
+      [
+        "▁cover",
+        -8.450661822121575
+      ],
+      [
+        "▁around",
+        -8.45801269553424
+      ],
+      [
+        "▁tru",
+        -8.465945416864763
+      ],
+      [
+        "▁free",
+        -8.466937917450903
+      ],
+      [
+        "▁death",
+        -8.471387109509486
+      ],
+      [
+        "▁character",
+        -8.47925380341218
+      ],
+      [
+        "▁cra",
+        -8.480388755035024
+      ],
+      [
+        "▁street",
+        -8.481857857041343
+      ],
+      [
+        "▁career",
+        -8.485696642742031
+      ],
+      [
+        "▁follow",
+        -8.487054795889959
+      ],
+      [
+        "▁little",
+        -8.493929657535503
+      ],
+      [
+        "▁daughter",
+        -8.495838031310194
+      ],
+      [
+        "▁right",
+        -8.49938327486857
+      ],
+      [
+        "▁blo",
+        -8.504736151694356
+      ],
+      [
+        "▁studie",
+        -8.507158028275926
+      ],
+      [
+        "▁title",
+        -8.507564681345778
+      ],
+      [
+        "▁power",
+        -8.511276797327884
+      ],
+      [
+        "▁held",
+        -8.515310155299764
+      ],
+      [
+        "ford",
+        -8.515923299326781
+      ],
+      [
+        "▁student",
+        -8.517949142703806
+      ],
+      [
+        "▁site",
+        -8.521783262108439
+      ],
+      [
+        "▁language",
+        -8.526534303494756
+      ],
+      [
+        "▁sign",
+        -8.530535229851592
+      ],
+      [
+        "▁person",
+        -8.532003665866414
+      ],
+      [
+        "▁dan",
+        -8.534603981452662
+      ],
+      [
+        "▁next",
+        -8.536724744790396
+      ],
+      [
+        "▁contain",
+        -8.53724021736098
+      ],
+      [
+        "▁written",
+        -8.537538191946581
+      ],
+      [
+        "▁built",
+        -8.537564784011852
+      ],
+      [
+        "▁english",
+        -8.541233022321085
+      ],
+      [
+        "▁manag",
+        -8.541411310908908
+      ],
+      [
+        "▁again",
+        -8.543463036773398
+      ],
+      [
+        "▁track",
+        -8.549096848636776
+      ],
+      [
+        "▁become",
+        -8.5505817092827
+      ],
+      [
+        "▁addition",
+        -8.563724537950346
+      ],
+      [
+        "ified",
+        -8.563753973454977
+      ],
+      [
+        "▁usual",
+        -8.566681752436955
+      ],
+      [
+        "▁get",
+        -8.567392155490447
+      ],
+      [
+        "▁availabl",
+        -8.571643418051458
+      ],
+      [
+        "▁center",
+        -8.574426393488245
+      ],
+      [
+        "uff",
+        -8.574573366537244
+      ],
+      [
+        "▁present",
+        -8.580592559305742
+      ],
+      [
+        "▁along",
+        -8.58128059442477
+      ],
+      [
+        "▁council",
+        -8.589140398796983
+      ],
+      [
+        "▁turn",
+        -8.592979495777078
+      ],
+      [
+        "▁green",
+        -8.598366406527138
+      ],
+      [
+        "▁count",
+        -8.601811261637131
+      ],
+      [
+        "▁mother",
+        -8.60917887040323
+      ],
+      [
+        "spect",
+        -8.616966412856792
+      ],
+      [
+        "▁look",
+        -8.623242916827012
+      ],
+      [
+        "▁london",
+        -8.623263516450116
+      ],
+      [
+        "ville",
+        -8.625035670776107
+      ],
+      [
+        "▁represent",
+        -8.625449075298462
+      ],
+      [
+        "▁history",
+        -8.625869986710171
+      ],
+      [
+        "▁version",
+        -8.631353483577167
+      ],
+      [
+        "▁international",
+        -8.634276172051226
+      ],
+      [
+        "▁court",
+        -8.634998422314329
+      ],
+      [
+        "▁various",
+        -8.635383508148188
+      ],
+      [
+        "▁president",
+        -8.636493086624457
+      ],
+      [
+        "▁business",
+        -8.636863367535444
+      ],
+      [
+        "▁among",
+        -8.64000108582483
+      ],
+      [
+        "▁flow",
+        -8.640479428725959
+      ],
+      [
+        "▁light",
+        -8.641530059379548
+      ],
+      [
+        "▁help",
+        -8.647441596103139
+      ],
+      [
+        "▁order",
+        -8.64861737687781
+      ],
+      [
+        "▁hill",
+        -8.65204824091686
+      ],
+      [
+        "▁complete",
+        -8.660665816625905
+      ],
+      [
+        "▁similar",
+        -8.66731645121796
+      ],
+      [
+        "▁week",
+        -8.669176248324836
+      ],
+      [
+        "▁word",
+        -8.669623600409947
+      ],
+      [
+        "▁offer",
+        -8.675409935441808
+      ],
+      [
+        "▁important",
+        -8.679221405674415
+      ],
+      [
+        "▁wife",
+        -8.680119542779103
+      ],
+      [
+        "▁third",
+        -8.680798513458852
+      ],
+      [
+        "▁europe",
+        -8.68425651958696
+      ],
+      [
+        "▁football",
+        -8.694794948303976
+      ],
+      [
+        "▁know",
+        -8.70808700609502
+      ],
+      [
+        "▁period",
+        -8.708236352219206
+      ],
+      [
+        "▁woman",
+        -8.70912189579257
+      ],
+      [
+        "▁species",
+        -8.712212355389836
+      ],
+      [
+        "▁blue",
+        -8.713037621854472
+      ],
+      [
+        "▁enter",
+        -8.713052698133598
+      ],
+      [
+        "against",
+        -8.714412797815836
+      ],
+      [
+        "▁settle",
+        -8.715915482394756
+      ],
+      [
+        "▁operate",
+        -8.717045325823666
+      ],
+      [
+        "▁author",
+        -8.717423149151815
+      ],
+      [
+        "▁exist",
+        -8.7253180719574
+      ],
+      [
+        "▁eight",
+        -8.728034899341813
+      ],
+      [
+        "▁project",
+        -8.729937576855761
+      ],
+      [
+        "▁sometimes",
+        -8.734008547807601
+      ],
+      [
+        "▁special",
+        -8.741374050821644
+      ],
+      [
+        "▁child",
+        -8.747484726940964
+      ],
+      [
+        "▁example",
+        -8.747572909454611
+      ],
+      [
+        "▁league",
+        -8.752544235031802
+      ],
+      [
+        "▁type",
+        -8.755095330832773
+      ],
+      [
+        "▁engine",
+        -8.759635996925297
+      ],
+      [
+        "▁collect",
+        -8.759859172926044
+      ],
+      [
+        "▁grow",
+        -8.762688448938803
+      ],
+      [
+        "▁surviv",
+        -8.763835496149287
+      ],
+      [
+        "▁though",
+        -8.765961027715528
+      ],
+      [
+        "▁level",
+        -8.772041953413918
+      ],
+      [
+        "▁british",
+        -8.781646781141653
+      ],
+      [
+        "burg",
+        -8.782109628693906
+      ],
+      [
+        "▁fish",
+        -8.785727132173403
+      ],
+      [
+        "▁eventual",
+        -8.78599819623117
+      ],
+      [
+        "▁walk",
+        -8.786273773044563
+      ],
+      [
+        "▁farm",
+        -8.787884660123996
+      ],
+      [
+        "▁friend",
+        -8.791545567410537
+      ],
+      [
+        "▁girl",
+        -8.792859715640407
+      ],
+      [
+        "▁describe",
+        -8.794135213475116
+      ],
+      [
+        "▁grand",
+        -8.797914720177122
+      ],
+      [
+        "▁pra",
+        -8.801743694975219
+      ],
+      [
+        "▁french",
+        -8.804636753869945
+      ],
+      [
+        "▁mountain",
+        -8.810740380898126
+      ],
+      [
+        "▁william",
+        -8.81213443408776
+      ],
+      [
+        "▁central",
+        -8.812514204231366
+      ],
+      [
+        "▁those",
+        -8.815268051810754
+      ],
+      [
+        "▁historic",
+        -8.817124151070487
+      ],
+      [
+        "▁should",
+        -8.822263968962837
+      ],
+      [
+        "bility",
+        -8.825843476855038
+      ],
+      [
+        "▁construct",
+        -8.82718187472506
+      ],
+      [
+        "ency",
+        -8.83150706603628
+      ],
+      [
+        "▁wrot",
+        -8.837571561595198
+      ],
+      [
+        "▁consist",
+        -8.842652643641848
+      ],
+      [
+        "▁australia",
+        -8.846626741298131
+      ],
+      [
+        "▁effect",
+        -8.847997803512609
+      ],
+      [
+        "▁process",
+        -8.84901200095267
+      ],
+      [
+        "▁replac",
+        -8.849360841452432
+      ],
+      [
+        "▁control",
+        -8.852403434628375
+      ],
+      [
+        "ology",
+        -8.852877971924125
+      ],
+      [
+        "▁england",
+        -8.854427120471016
+      ],
+      [
+        "▁includ",
+        -8.85878984229386
+      ],
+      [
+        "���write",
+        -8.860317339202346
+      ],
+      [
+        "▁further",
+        -8.86090855209244
+      ],
+      [
+        "▁position",
+        -8.866286184735717
+      ],
+      [
+        "▁women",
+        -8.86696169453236
+      ],
+      [
+        "▁together",
+        -8.869799173981853
+      ],
+      [
+        "▁video",
+        -8.887124180111755
+      ],
+      [
+        "▁occur",
+        -8.888124747828993
+      ],
+      [
+        "▁previous",
+        -8.896255937560948
+      ],
+      [
+        "▁involve",
+        -8.89721391467737
+      ],
+      [
+        "▁require",
+        -8.898803593163606
+      ],
+      [
+        "▁issue",
+        -8.902682904684076
+      ],
+      [
+        "▁model",
+        -8.903230207757918
+      ],
+      [
+        "▁centre",
+        -8.912180621179559
+      ],
+      [
+        "▁official",
+        -8.912705660016188
+      ],
+      [
+        "▁education",
+        -8.922018097144344
+      ],
+      [
+        "▁subsequent",
+        -8.922510440111688
+      ],
+      [
+        "▁cemetery",
+        -8.931419209988611
+      ],
+      [
+        "▁director",
+        -8.935937539574503
+      ],
+      [
+        "▁battle",
+        -8.947502148354001
+      ],
+      [
+        "▁museum",
+        -8.951512658304399
+      ],
+      [
+        "▁northern",
+        -8.951916463250939
+      ],
+      [
+        "▁artist",
+        -8.953811567205221
+      ],
+      [
+        "▁research",
+        -8.964268273840068
+      ],
+      [
+        "▁strong",
+        -8.965970223651727
+      ],
+      [
+        "▁market",
+        -8.968622701662255
+      ],
+      [
+        "▁political",
+        -8.973039284330682
+      ],
+      [
+        "▁problem",
+        -8.973559619952457
+      ],
+      [
+        "▁review",
+        -8.975638997595691
+      ],
+      [
+        "▁sound",
+        -8.975977122352809
+      ],
+      [
+        "▁style",
+        -8.976176394221653
+      ],
+      [
+        "▁leave",
+        -8.977548989088348
+      ],
+      [
+        "▁california",
+        -8.980843398409057
+      ],
+      [
+        "▁attack",
+        -8.982962739927693
+      ],
+      [
+        "▁range",
+        -8.985729838044836
+      ],
+      [
+        "▁organiz",
+        -8.988726922831367
+      ],
+      [
+        "▁brown",
+        -8.998720503761433
+      ],
+      [
+        "▁western",
+        -8.999643026933589
+      ],
+      [
+        "▁novel",
+        -9.000218912912711
+      ],
+      [
+        "▁modern",
+        -9.001985996102455
+      ],
+      [
+        "▁independen",
+        -9.003025460321094
+      ],
+      [
+        "▁champion",
+        -9.003031332715086
+      ],
+      [
+        "▁round",
+        -9.01089257525527
+      ],
+      [
+        "▁always",
+        -9.014031753493049
+      ],
+      [
+        "until",
+        -9.017485978405505
+      ],
+      [
+        "▁limit",
+        -9.017747642672813
+      ],
+      [
+        "▁capital",
+        -9.025208555516956
+      ],
+      [
+        "▁nav",
+        -9.036214093417485
+      ],
+      [
+        "stead",
+        -9.038761616772518
+      ],
+      [
+        "▁sister",
+        -9.041954428574062
+      ],
+      [
+        "▁bridge",
+        -9.043474718270652
+      ],
+      [
+        "hood",
+        -9.053521622777172
+      ],
+      [
+        "▁source",
+        -9.062504658078463
+      ],
+      [
+        "▁middle",
+        -9.070992453580974
+      ],
+      [
+        "▁entire",
+        -9.077889166105958
+      ],
+      [
+        "▁origin",
+        -9.08432968742058
+      ],
+      [
+        "▁private",
+        -9.088282545245027
+      ],
+      [
+        "▁railway",
+        -9.09176405323294
+      ],
+      [
+        "script",
+        -9.095365653342965
+      ],
+      [
+        "▁establish",
+        -9.097614929235975
+      ],
+      [
+        "▁course",
+        -9.098861308440863
+      ],
+      [
+        "▁military",
+        -9.099377861676238
+      ],
+      [
+        "▁method",
+        -9.114198214049043
+      ],
+      [
+        "▁television",
+        -9.117176904131602
+      ],
+      [
+        "▁social",
+        -9.117818473849477
+      ],
+      [
+        "▁civil",
+        -9.11898023552438
+      ],
+      [
+        "▁border",
+        -9.123240593057512
+      ],
+      [
+        "▁travel",
+        -9.135767295622834
+      ],
+      [
+        "▁africa",
+        -9.137135089263122
+      ],
+      [
+        "▁numerous",
+        -9.140187327155555
+      ],
+      [
+        "ograph",
+        -9.141979637162184
+      ],
+      [
+        "▁canada",
+        -9.14829270959714
+      ],
+      [
+        "▁typical",
+        -9.151275066866766
+      ],
+      [
+        "▁resident",
+        -9.153758592596224
+      ],
+      [
+        "embl",
+        -9.156516831069087
+      ],
+      [
+        "▁practice",
+        -9.161235920546735
+      ],
+      [
+        "▁separate",
+        -9.161865477490087
+      ],
+      [
+        "▁drive",
+        -9.164561808409092
+      ],
+      [
+        "▁episode",
+        -9.168139434816258
+      ],
+      [
+        "▁surround",
+        -9.17192615052093
+      ],
+      [
+        "▁structure",
+        -9.177633273927295
+      ],
+      [
+        "▁particular",
+        -9.17763354042183
+      ],
+      [
+        "▁believe",
+        -9.180274459538897
+      ],
+      [
+        "▁george",
+        -9.18337981163793
+      ],
+      [
+        "▁almost",
+        -9.188504152905503
+      ],
+      [
+        "▁primary",
+        -9.205397585951523
+      ],
+      [
+        "▁oppos",
+        -9.207991380266536
+      ],
+      [
+        "▁parish",
+        -9.20929604698349
+      ],
+      [
+        "▁valley",
+        -9.211974501351284
+      ],
+      [
+        "▁radio",
+        -9.21382264807512
+      ],
+      [
+        "▁municipal",
+        -9.220510803902828
+      ],
+      [
+        "▁population",
+        -9.220510979344862
+      ],
+      [
+        "▁natural",
+        -9.241981256185802
+      ],
+      [
+        "▁commercial",
+        -9.244697406730166
+      ],
+      [
+        "▁influence",
+        -9.25495085346992
+      ],
+      [
+        "▁across",
+        -9.256326284814747
+      ],
+      [
+        "▁increase",
+        -9.256327258400416
+      ],
+      [
+        "▁regular",
+        -9.25770439125096
+      ],
+      [
+        "▁facilit",
+        -9.259084648852792
+      ],
+      [
+        "▁america",
+        -9.263962803540426
+      ],
+      [
+        "▁hospital",
+        -9.269483647188489
+      ],
+      [
+        "▁chief",
+        -9.27440782920186
+      ],
+      [
+        "▁significant",
+        -9.275777252665556
+      ],
+      [
+        "▁department",
+        -9.277884028156835
+      ],
+      [
+        "▁elected",
+        -9.27858792830147
+      ],
+      [
+        "▁industry",
+        -9.287774883201791
+      ],
+      [
+        "▁information",
+        -9.288484870034107
+      ],
+      [
+        "▁occasion",
+        -9.292756790528593
+      ],
+      [
+        "▁possibl",
+        -9.293471685050614
+      ],
+      [
+        "▁voice",
+        -9.294308454586137
+      ],
+      [
+        "▁russia",
+        -9.294524578818091
+      ],
+      [
+        "▁frequent",
+        -9.296331052513468
+      ],
+      [
+        "▁writing",
+        -9.30280302036764
+      ],
+      [
+        "▁society",
+        -9.306406437689832
+      ],
+      [
+        "▁appoint",
+        -9.307138209700025
+      ],
+      [
+        "▁employ",
+        -9.307854252148935
+      ],
+      [
+        "▁subject",
+        -9.31658466568389
+      ],
+      [
+        "▁contribut",
+        -9.317316164023172
+      ],
+      [
+        "▁attempt",
+        -9.326130278902296
+      ],
+      [
+        "▁festival",
+        -9.33875041448835
+      ],
+      [
+        "▁headquarter",
+        -9.340994140116074
+      ],
+      [
+        "▁magazine",
+        -9.34174318900008
+      ],
+      [
+        "▁introduc",
+        -9.347003718055843
+      ],
+      [
+        "▁select",
+        -9.347576876301837
+      ],
+      [
+        "▁protect",
+        -9.35080352014047
+      ],
+      [
+        "▁republic",
+        -9.35836616238581
+      ],
+      [
+        "▁individual",
+        -9.362948072222718
+      ],
+      [
+        "▁except",
+        -9.364534105456542
+      ],
+      [
+        "▁studio",
+        -9.3667824469869
+      ],
+      [
+        "▁david",
+        -9.367555460558028
+      ],
+      [
+        "▁study",
+        -9.37449627486125
+      ],
+      [
+        "”",
+        -9.379152128763874
+      ],
+      [
+        "▁yellow",
+        -9.385398534472024
+      ],
+      [
+        "▁professional",
+        -9.390102570312028
+      ],
+      [
+        "▁christian",
+        -9.39167678588908
+      ],
+      [
+        "“",
+        -9.39720599339324
+      ],
+      [
+        "▁competition",
+        -9.399590054766064
+      ],
+      [
+        "▁architect",
+        -9.401969807983903
+      ],
+      [
+        "▁associate",
+        -9.40595717077596
+      ],
+      [
+        "▁network",
+        -9.413174416029864
+      ],
+      [
+        "▁platform",
+        -9.418824128957128
+      ],
+      [
+        "▁province",
+        -9.41882530778206
+      ],
+      [
+        "▁educate",
+        -9.4285931028375
+      ],
+      [
+        "▁succeed",
+        -9.43268361268196
+      ],
+      [
+        "▁experience",
+        -9.438440784217477
+      ],
+      [
+        "▁object",
+        -9.445066983476966
+      ],
+      [
+        "▁association",
+        -9.44672910556617
+      ],
+      [
+        "▁difficult",
+        -9.455926485547485
+      ],
+      [
+        "▁immediate",
+        -9.458449618275022
+      ],
+      [
+        "▁journal",
+        -9.462670239021836
+      ],
+      [
+        "▁observ",
+        -9.48492694663403
+      ],
+      [
+        "▁academy",
+        -9.490103247109989
+      ],
+      [
+        "▁committee",
+        -9.51118439539725
+      ],
+      [
+        "▁specific",
+        -9.512072499477846
+      ],
+      [
+        "▁newspaper",
+        -9.516524937949235
+      ],
+      [
+        "▁catholic",
+        -9.5201015950536
+      ],
+      [
+        "▁certain",
+        -9.523690778511131
+      ],
+      [
+        "incorporate",
+        -9.551951131559653
+      ],
+      [
+        "▁economic",
+        -9.553801898702435
+      ],
+      [
+        "‘",
+        -9.57155936963102
+      ],
+      [
+        "▁instrument",
+        -9.574392626922052
+      ],
+      [
+        "▁parliament",
+        -9.582939295715178
+      ],
+      [
+        "▁distinct",
+        -9.58775500128628
+      ],
+      [
+        "▁unknown",
+        -9.589637899752152
+      ],
+      [
+        "▁distribut",
+        -9.59348595392874
+      ],
+      [
+        "▁manufactur",
+        -9.611968904963938
+      ],
+      [
+        "specially",
+        -9.619871974666424
+      ],
+      [
+        "▁michael",
+        -9.63883651220214
+      ],
+      [
+        "▁democrat",
+        -9.639845273542909
+      ],
+      [
+        "▁affect",
+        -9.682130226089695
+      ],
+      [
+        "▁broadcast",
+        -9.691643496522142
+      ],
+      [
+        "▁electric",
+        -9.703408357083504
+      ],
+      [
+        "▁railroad",
+        -9.71858476735134
+      ],
+      [
+        "▁institute",
+        -9.738442109092423
+      ],
+      [
+        "▁virginia",
+        -9.7782199841132
+      ],
+      [
+        "▁executive",
+        -9.778219992852405
+      ],
+      [
+        "▁nickname",
+        -9.788709584330268
+      ],
+      [
+        "▁principal",
+        -9.796944922609374
+      ],
+      [
+        "▁technique",
+        -9.83670919121584
+      ],
+      [
+        "▁environment",
+        -9.865389459222612
+      ],
+      [
+        "q",
+        -9.876882881751468
+      ],
+      [
+        "▁basketball",
+        -9.888423102346794
+      ],
+      [
+        "▁recogniz",
+        -9.913326174623208
+      ],
+      [
+        "▁investigat",
+        -9.934789091309357
+      ],
+      [
+        "▁administrative",
+        -10.088374855936404
+      ],
+      [
+        "—",
+        -10.109142371045758
+      ],
+      [
+        "▁pennsylvania",
+        -10.136967400536996
+      ],
+      [
+        "▁metropolitan",
+        -10.141959090291545
+      ],
+      [
+        "▁massachusetts",
+        -10.170725872445
+      ],
+      [
+        "é",
+        -11.174417433920302
+      ],
+      [
+        "–",
+        -11.453548440521548
+      ],
+      [
+        "ü",
+        -11.524090256941632
+      ],
+      [
+        "ä",
+        -12.089533105118232
+      ],
+      [
+        "ö",
+        -12.296719802233156
+      ],
+      [
+        "á",
+        -12.435400432633775
+      ],
+      [
+        "í",
+        -12.577226894888064
+      ],
+      [
+        "ó",
+        -12.742544952256411
+      ],
+      [
+        "ç",
+        -13.120283714665124
+      ],
+      [
+        "â",
+        -13.339312667832004
+      ],
+      [
+        "ß",
+        -13.339312667832004
+      ],
+      [
+        "à",
+        -13.380979334498672
+      ],
+      [
+        "ō",
+        -13.734541852356523
+      ],
+      [
+        "ú",
+        -13.79704185235653
+      ],
+      [
+        "ô",
+        -14.095393500708347
+      ],
+      [
+        "ï",
+        -14.18630259161771
+      ],
+      [
+        "ł",
+        -14.522413702741172
+      ],
+      [
+        "ã",
+        -14.522413702741174
+      ],
+      [
+        "…",
+        -14.522413702741174
+      ],
+      [
+        "ë",
+        -14.665270845598318
+      ],
+      [
+        "ć",
+        -14.831937512264984
+      ],
+      [
+        "ø",
+        -14.831937512304942
+      ],
+      [
+        "č",
+        -14.831937512304943
+      ],
+      [
+        "ă",
+        -15.031937512304935
+      ],
+      [
+        "´",
+        -15.281937512264983
+      ],
+      [
+        "š",
+        -15.281937512264989
+      ],
+      [
+        "î",
+        -15.281937512304944
+      ],
+      [
+        "û",
+        -15.61527084559832
+      ],
+      [
+        "ž",
+        -15.615270845598324
+      ],
+      [
+        "ș",
+        -15.615270845638266
+      ],
+      [
+        "ò",
+        -15.615270845638276
+      ],
+      [
+        "ā",
+        -15.615270845638276
+      ],
+      [
+        "]",
+        -15.615270845638276
+      ],
+      [
+        "ř",
+        -16.115270845598324
+      ],
+      [
+        "ş",
+        -16.11527084563828
+      ],
+      [
+        "ı",
+        -16.11527084563828
+      ],
+      [
+        "α",
+        -16.11527084563828
+      ],
+      [
+        "å",
+        -16.11527084563828
+      ],
+      [
+        "»",
+        -16.11527084563828
+      ],
+      [
+        "ʻ",
+        -16.11527084563828
+      ],
+      [
+        "π",
+        -17.114470845638277
+      ],
+      [
+        "œ",
+        -17.11457084563828
+      ],
+      [
+        "«",
+        -17.11467084563828
+      ],
+      [
+        "·",
+        -17.11477084563828
+      ],
+      [
+        "ū",
+        -17.11487084563828
+      ],
+      [
+        "è",
+        -17.11497084563828
+      ],
+      [
+        "[",
+        -17.11507084563828
+      ],
+      [
+        "ê",
+        -17.11517084563828
+      ],
+      [
+        "ạ",
+        -17.115270845598324
+      ],
+      [
+        "ī",
+        -17.115270845638264
+      ],
+      [
+        "阪",
+        -17.11527084563828
+      ],
+      [
+        "京",
+        -17.11527084563828
+      ],
+      [
+        "→",
+        -17.11527084563828
+      ],
+      [
+        "χ",
+        -17.11527084563828
+      ],
+      [
+        "ע",
+        -17.11527084563828
+      ],
+      [
+        "ị",
+        -17.11527084563828
+      ],
+      [
+        "ð",
+        -17.11527084563828
+      ],
+      [
+        "熊",
+        -17.11527084563828
+      ],
+      [
+        "а",
+        -17.11527084563828
+      ],
+      [
+        "ñ",
+        -17.11527084563828
+      ],
+      [
+        "ả",
+        -17.11527084563828
+      ],
+      [
+        "ő",
+        -17.11527084563828
+      ],
+      [
+        "大",
+        -17.11527084563828
+      ],
+      [
+        "时",
+        -17.11527084563828
+      ],
+      [
+        "ń",
+        -17.11527084563828
+      ],
+      [
+        "ý",
+        -17.11527084563828
+      ],
+      [
+        "尚",
+        -17.11527084563828
+      ],
+      [
+        "先",
+        -17.11527084563828
+      ],
+      [
+        "€",
+        -17.11527084563828
+      ],
+      [
+        "„",
+        -17.11527084563828
+      ],
+      [
+        "奔",
+        -17.11527084563828
+      ],
+      [
+        "生",
+        -17.11527084563828
+      ],
+      [
+        "¡",
+        -17.11527084563828
+      ],
+      [
+        "都",
+        -17.11527084563828
+      ],
+      [
+        "נ",
+        -17.11527084563828
+      ],
+      [
+        "ň",
+        -17.11527084563828
+      ]
+    ],
+    "byte_fallback": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "([bos])",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "([eos])",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "([unk])",
+      "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
+    },
+    "4": {
+      "content": "([mask])",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "([bos])",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "([eos])",
+  "mask_token": "([mask])",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "([pad])",
+  "sep_token": "▁",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "([unk])"
+}