Upload 7 files

config.json

@@ -0,0 +1,173 @@
+{
+  "_name_or_path": "./model/",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 384,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layernorm_embedding": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "trocr",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "use_learned_position_embeddings": true,
+    "vocab_size": 1000
+  },
+  "decoder_start_token_id": 1,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "deit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 6,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "vocab_size": 1000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 512,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18185036b87f4aeaf570d0c721c229185d7d3e11c22c83edd1da701df02ff25f
+size 117316160

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DeiTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "TrOCRProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,1996 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": true,
+      "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": "RobertaProcessing",
+    "sep": [
+      "</s>",
+      2
+    ],
+    "cls": [
+      "<s>",
+      1
+    ],
+    "trim_offsets": true,
+    "add_prefix_space": 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,
+    "ignore_merges": false,
+    "vocab": {
+      "<pad>": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "<unk>": 3,
+      "<mask>": 4,
+      "!": 5,
+      "\"": 6,
+      "&": 7,
+      "'": 8,
+      "(": 9,
+      ")": 10,
+      "*": 11,
+      "+": 12,
+      ",": 13,
+      "-": 14,
+      ".": 15,
+      "/": 16,
+      "0": 17,
+      "1": 18,
+      "2": 19,
+      "3": 20,
+      "4": 21,
+      "5": 22,
+      "6": 23,
+      "7": 24,
+      "8": 25,
+      "9": 26,
+      ":": 27,
+      ";": 28,
+      "<": 29,
+      "=": 30,
+      ">": 31,
+      "?": 32,
+      "@": 33,
+      "A": 34,
+      "B": 35,
+      "C": 36,
+      "D": 37,
+      "E": 38,
+      "F": 39,
+      "G": 40,
+      "H": 41,
+      "I": 42,
+      "J": 43,
+      "K": 44,
+      "L": 45,
+      "M": 46,
+      "N": 47,
+      "O": 48,
+      "P": 49,
+      "Q": 50,
+      "R": 51,
+      "S": 52,
+      "T": 53,
+      "U": 54,
+      "V": 55,
+      "W": 56,
+      "X": 57,
+      "Y": 58,
+      "Z": 59,
+      "[": 60,
+      "\\": 61,
+      "]": 62,
+      "^": 63,
+      "_": 64,
+      "`": 65,
+      "a": 66,
+      "b": 67,
+      "c": 68,
+      "d": 69,
+      "e": 70,
+      "f": 71,
+      "g": 72,
+      "h": 73,
+      "i": 74,
+      "j": 75,
+      "k": 76,
+      "l": 77,
+      "m": 78,
+      "n": 79,
+      "o": 80,
+      "p": 81,
+      "q": 82,
+      "r": 83,
+      "s": 84,
+      "t": 85,
+      "u": 86,
+      "v": 87,
+      "w": 88,
+      "x": 89,
+      "y": 90,
+      "z": 91,
+      "{": 92,
+      "|": 93,
+      "}": 94,
+      "Ġ": 95,
+      "Ġ)": 96,
+      "Ġ(": 97,
+      "Ġ_": 98,
+      "Ġ^": 99,
+      "Ġ1": 100,
+      "Ġ,": 101,
+      "Ġ-": 102,
+      "Ġ2": 103,
+      "Ġ=": 104,
+      "Ġ+": 105,
+      "Ġi": 106,
+      "Ġd": 107,
+      "Ġt": 108,
+      "Ġn": 109,
+      "Ġx": 110,
+      "Ġa": 111,
+      "Ġ/": 112,
+      "Ġs": 113,
+      "Ġp": 114,
+      "Ġ0": 115,
+      "ta": 116,
+      "Ġk": 117,
+      "Ġm": 118,
+      "Ġ|": 119,
+      "Ġb": 120,
+      "al": 121,
+      "Ġe": 122,
+      "Ġu": 123,
+      "Ġl": 124,
+      "Ġj": 125,
+      "Ġ.": 126,
+      "Ġc": 127,
+      "Ġ&": 128,
+      "am": 129,
+      "Ġo": 130,
+      "Ġr": 131,
+      "ha": 132,
+      "Ġg": 133,
+      "eta": 134,
+      "eg": 135,
+      "Ġz": 136,
+      "ma": 137,
+      "Ġ\\": 138,
+      "Ġin": 139,
+      "hi": 140,
+      "Ġf": 141,
+      "ig": 142,
+      "Ġy": 143,
+      "in": 144,
+      "Ġq": 145,
+      "pha": 146,
+      "ot": 147,
+      "il": 148,
+      "Ġal": 149,
+      "Ġalpha": 150,
+      "Ġ3": 151,
+      "Ġdot": 152,
+      "da": 153,
+      "amb": 154,
+      "ambda": 155,
+      "um": 156,
+      "el": 157,
+      "Ġsum": 158,
+      "Ġv": 159,
+      "ĠA": 160,
+      "Ġ]": 161,
+      "alt": 162,
+      "ĠP": 163,
+      "Ġdi": 164,
+      "Ġmu": 165,
+      "Ġlambda": 166,
+      "Ġ<": 167,
+      "Ġ[": 168,
+      "Ġphi": 169,
+      "ral": 170,
+      "de": 171,
+      "ĠN": 172,
+      "le": 173,
+      "ĠT": 174,
+      "elta": 175,
+      "amma": 176,
+      "Ġdif": 177,
+      "ĠL": 178,
+      "ĠD": 179,
+      "ĠX": 180,
+      "teg": 181,
+      "tegral": 182,
+      "im": 183,
+      "Ġdiff": 184,
+      "Ġ4": 185,
+      "Ġh": 186,
+      "er": 187,
+      "pr": 188,
+      "Ġintegral": 189,
+      "igh": 190,
+      "ight": 191,
+      "pright": 192,
+      "ine": 193,
+      "line": 194,
+      "ega": 195,
+      "mega": 196,
+      "Ġupright": 197,
+      "ĠR": 198,
+      "Ġw": 199,
+      "on": 200,
+      "ĠB": 201,
+      "ilde": 202,
+      "ĠG": 203,
+      "ver": 204,
+      "verline": 205,
+      "Ġbeta": 206,
+      "heta": 207,
+      "igma": 208,
+      "Ġ<=": 209,
+      "ĠS": 210,
+      "Ġcal": 211,
+      "Ġpi": 212,
+      "Ġoverline": 213,
+      "Ġoo": 214,
+      "ps": 215,
+      "Ġ||": 216,
+      "Ġdots": 217,
+      "Ġan": 218,
+      "ĠM": 219,
+      "Ġtheta": 220,
+      "ĠC": 221,
+      "Ġtilde": 222,
+      "ilon": 223,
+      "psilon": 224,
+      "ĠH": 225,
+      "ho": 226,
+      "Ġ*": 227,
+      "Ġgamma": 228,
+      "ĠF": 229,
+      "Ġ:": 230,
+      "gle": 231,
+      "Ġepsilon": 232,
+      "si": 233,
+      "Ġsigma": 234,
+      "Ġta": 235,
+      "Ġxi": 236,
+      "Ġdelta": 237,
+      "Ġtau": 238,
+      "Ġnu": 239,
+      "ĠE": 240,
+      "ol": 241,
+      "es": 242,
+      "Ġrho": 243,
+      "old": 244,
+      "Ġangle": 245,
+      "Ġ>": 246,
+      "ĠI": 247,
+      "Ġ\"": 248,
+      "Ġbold": 249,
+      "hat": 250,
+      "Ġomega": 251,
+      "ĠO": 252,
+      "ĠK": 253,
+      "la": 254,
+      "ĠV": 255,
+      "Ġeta": 256,
+      "us": 257,
+      "Ġpsi": 258,
+      "Ġhat": 259,
+      "ro": 260,
+      "Ġ}": 261,
+      "rt": 262,
+      "qrt": 263,
+      "Ġsqrt": 264,
+      "Ġ{": 265,
+      "imes": 266,
+      "ĠQ": 267,
+      "Ġtimes": 268,
+      "ll": 269,
+      "Ġell": 270,
+      "Ġbb": 271,
+      "Ġ\\;": 272,
+      "ĠU": 273,
+      "ab": 274,
+      "ĠY": 275,
+      "abla": 276,
+      "Ġnabla": 277,
+      "ĠJ": 278,
+      "ĠZ": 279,
+      "om": 280,
+      "ĠW": 281,
+      "rc": 282,
+      "Ġ->": 283,
+      "ĠDelta": 284,
+      "irc": 285,
+      "ircle": 286,
+      "Ġ>=": 287,
+      "ct": 288,
+      "circle": 289,
+      "os": 290,
+      "ĠOmega": 291,
+      "ĠGamma": 292,
+      "og": 293,
+      "Ġ!": 294,
+      "Ġlog": 295,
+      "lus": 296,
+      "ĠPhi": 297,
+      "Ġchi": 298,
+      "Ġ5": 299,
+      "du": 300,
+      "Ġplus": 301,
+      "row": 302,
+      "Ġzeta": 303,
+      "Ġlr": 304,
+      "pa": 305,
+      "ap": 306,
+      "rrow": 307,
+      "appa": 308,
+      "inus": 309,
+      "Ġarrow": 310,
+      "Ġ6": 311,
+      "ĠLambda": 312,
+      "duct": 313,
+      "Ġkappa": 314,
+      "Ġpro": 315,
+      "Ġma": 316,
+      "Ġproduct": 317,
+      "minus": 318,
+      "st": 319,
+      "omp": 320,
+      "ose": 321,
+      "Ġcomp": 322,
+      "Ġcompose": 323,
+      "Ġ;": 324,
+      "ua": 325,
+      "Ġdel": 326,
+      "Ġdelim": 327,
+      "ide": 328,
+      "uad": 329,
+      "inom": 330,
+      "Ġquad": 331,
+      "as": 332,
+      "Ġbinom": 333,
+      "ases": 334,
+      "cal": 335,
+      "Ġlim": 336,
+      "ĠPsi": 337,
+      "ra": 338,
+      "sum": 339,
+      "an": 340,
+      "Ġ8": 341,
+      "Ġsu": 342,
+      "Ġsin": 343,
+      "Ġ12": 344,
+      "Ġun": 345,
+      "bs": 346,
+      "Ġcos": 347,
+      "rak": 348,
+      "Ġ'": 349,
+      "Ġast": 350,
+      "Ġ\\{": 351,
+      "Ġ\\}": 352,
+      "Ġand": 353,
+      "et": 354,
+      "xp": 355,
+      "Ġmat": 356,
+      "ts": 357,
+      "Ġse": 358,
+      "Ġsect": 359,
+      "Ġfrak": 360,
+      "tilde": 361,
+      "iv": 362,
+      "Ġexp": 363,
+      "Ġ\"(": 364,
+      "Ġ\"(\"": 365,
+      "integral": 366,
+      "qu": 367,
+      "quiv": 368,
+      "rall": 369,
+      "ĠSigma": 370,
+      "Ġpr": 371,
+      "Ġcases": 372,
+      "lim": 373,
+      "ri": 374,
+      "orall": 375,
+      "Ġ!=": 376,
+      "ime": 377,
+      "Ġprime": 378,
+      "Ġequiv": 379,
+      "Ġln": 380,
+      "ag": 381,
+      "Ġwide": 382,
+      "Ġdiv": 383,
+      "Ġforall": 384,
+      "ides": 385,
+      "Ġdivides": 386,
+      "ger": 387,
+      "Ġdag": 388,
+      "Ġdagger": 389,
+      "..": 390,
+      "phi": 391,
+      "Ġ11": 392,
+      "angle": 393,
+      "Ġ7": 394,
+      "Ġmax": 395,
+      "Ġ)'": 396,
+      "eq": 397,
+      "ck": 398,
+      "re": 399,
+      "Ġabs": 400,
+      "ion": 401,
+      "lan": 402,
+      "Ġsup": 403,
+      "Ġ...": 404,
+      "if": 405,
+      "der": 406,
+      "derline": 407,
+      "ĠPi": 408,
+      "Ġunion": 409,
+      "rip": 410,
+      "ĠTheta": 411,
+      "crip": 412,
+      "cripts": 413,
+      "Ġunderline": 414,
+      "||": 415,
+      "wj": 416,
+      "Ġsubs": 417,
+      "Ġsubset": 418,
+      "dif": 419,
+      "Ġscripts": 420,
+      "cases": 421,
+      "Ġ9": 422,
+      "Ġmin": 423,
+      "tar": 424,
+      "Ġstar": 425,
+      "diff": 426,
+      "Ġ10": 427,
+      "Ġlt": 428,
+      "Ġzwj": 429,
+      "do": 430,
+      "its": 431,
+      "Ġlimits": 432,
+      "ut": 433,
+      "overline": 434,
+      "delta": 435,
+      "it": 436,
+      "Ġop": 437,
+      "or": 438,
+      "ans": 439,
+      "Delta": 440,
+      "ec": 441,
+      "hout": 442,
+      "Ġwit": 443,
+      "Ġwithout": 444,
+      "Ġ\"[": 445,
+      "Ġ\"[\"": 446,
+      "Ġdet": 447,
+      "ub": 448,
+      "->": 449,
+      "doub": 450,
+      "double": 451,
+      "Ġsans": 452,
+      "ce": 453,
+      "erp": 454,
+      "Ġperp": 455,
+      "bold": 456,
+      "redu": 457,
+      "reduce": 458,
+      "lanck": 459,
+      "Ġplanck": 460,
+      "lambda": 461,
+      "op": 462,
+      "alpha": 463,
+      "Ġ16": 464,
+      "psi": 465,
+      "ota": 466,
+      "Ġinf": 467,
+      "ed": 468,
+      "mu": 469,
+      "ked": 470,
+      "roked": 471,
+      "stroked": 472,
+      "rho": 473,
+      "Ġor": 474,
+      "pro": 475,
+      "Ġiota": 476,
+      "sigma": 477,
+      "Phi": 478,
+      "Ġ22": 479,
+      "Ġ21": 480,
+      "Ġ13": 481,
+      "gamma": 482,
+      "bb": 483,
+      "ar": 484,
+      "dot": 485,
+      "Ġ24": 486,
+      "orm": 487,
+      "Ġdim": 488,
+      "omega": 489,
+      "od": 490,
+      "lr": 491,
+      "lant": 492,
+      "slant": 493,
+      "hin": 494,
+      "Ġ23": 495,
+      "xi": 496,
+      "theta": 497,
+      "Ġsinh": 498,
+      "Ġvec": 499,
+      "riangle": 500,
+      "Gamma": 501,
+      "mod": 502,
+      "beta": 503,
+      "Ġcosh": 504,
+      "tau": 505,
+      "pi": 506,
+      "Ġtriangle": 507,
+      "nabla": 508,
+      "Ġnorm": 509,
+      "prox": 510,
+      "Ġtop": 511,
+      "pprox": 512,
+      "Ġapprox": 513,
+      "aron": 514,
+      "Psi": 515,
+      "ul": 516,
+      "let": 517,
+      "ullet": 518,
+      "Ġbullet": 519,
+      "Ġ|->": 520,
+      "chi": 521,
+      "Ġminus": 522,
+      "plus": 523,
+      "epsilon": 524,
+      "Ġcaron": 525,
+      "ĠRe": 526,
+      "Tr": 527,
+      "crow": 528,
+      "ilcrow": 529,
+      "Ġ14": 530,
+      "Ġ-->": 531,
+      "Ġtan": 532,
+      "Lambda": 533,
+      "Ġ32": 534,
+      "Ġdeg": 535,
+      "Omega": 536,
+      "00": 537,
+      "ic": 538,
+      "Ġnot": 539,
+      "ĠXi": 540,
+      "all": 541,
+      "las": 542,
+      "nu": 543,
+      "ack": 544,
+      "slas": 545,
+      "Ġback": 546,
+      "slash": 547,
+      "Ġbackslash": 548,
+      "hing": 549,
+      "Ġnothing": 550,
+      "ss": 551,
+      "Ġ15": 552,
+      "tr": 553,
+      "frak": 554,
+      "det": 555,
+      "sq": 556,
+      "Ġ20": 557,
+      "=>": 558,
+      "less": 559,
+      "Ġgt": 560,
+      "abs": 561,
+      "Ġpilcrow": 562,
+      "Ġdotless": 563,
+      "mat": 564,
+      "zeta": 565,
+      "and": 566,
+      "{\"": 567,
+      "Ġ\"{\"": 568,
+      "lic": 569,
+      "talic": 570,
+      "dim": 571,
+      "vec": 572,
+      "Ġ01": 573,
+      "product": 574,
+      "uare": 575,
+      "upright": 576,
+      "con": 577,
+      "not": 578,
+      "kappa": 579,
+      "up": 580,
+      "Ġitalic": 581,
+      "Ġ00": 582,
+      "equiv": 583,
+      "sup": 584,
+      "Ġ=>": 585,
+      "ĠUpsilon": 586,
+      "lo": 587,
+      "sm": 588,
+      "rev": 589,
+      "Ġcot": 590,
+      "small": 591,
+      "Ġ25": 592,
+      "Ġthin": 593,
+      "ĠIm": 594,
+      "div": 595,
+      "cont": 596,
+      "Ġ18": 597,
+      "Ġ31": 598,
+      "Ġupsilon": 599,
+      "Ġbot": 600,
+      "wn": 601,
+      "down": 602,
+      "Pi": 603,
+      "log": 604,
+      "Sigma": 605,
+      "Theta": 606,
+      "sts": 607,
+      "xists": 608,
+      "Ġ34": 609,
+      "arrow": 610,
+      "max": 611,
+      "min": 612,
+      "ong": 613,
+      "long": 614,
+      "Ġ33": 615,
+      "square": 616,
+      "exp": 617,
+      "Re": 618,
+      "di": 619,
+      "rack": 620,
+      "loor": 621,
+      "racket": 622,
+      "Ġexists": 623,
+      "Ġker": 624,
+      "ell": 625,
+      "Ġ<==>": 626,
+      "Ġfloor": 627,
+      "Ġtanh": 628,
+      "ono": 629,
+      "Ġ27": 630,
+      "rallel": 631,
+      "ĠPr": 632,
+      "Ġ123": 633,
+      "reve": 634,
+      "zwj": 635,
+      "Ġ17": 636,
+      "un": 637,
+      "for": 638,
+      "arallel": 639,
+      "Ġparallel": 640,
+      "Ġ==>": 641,
+      "Ġ48": 642,
+      "Ġmono": 643,
+      "Ġprec": 644,
+      "rg": 645,
+      "Ġ<=>": 646,
+      "Im": 647,
+      "Ġ36": 648,
+      "forall": 649,
+      "Ġ19": 650,
+      "12": 651,
+      "binom": 652,
+      "pset": 653,
+      "Ġsupset": 654,
+      "Ġbreve": 655,
+      "Ġ30": 656,
+      "Ġarg": 657,
+      "Ġcircle": 658,
+      "Ġbracket": 659,
+      "tan": 660,
+      "ond": 661,
+      "norm": 662,
+      "amond": 663,
+      "Ġdiamond": 664,
+      "sqrt": 665,
+      "cd": 666,
+      "allot": 667,
+      "Ġ64": 668,
+      "ff": 669,
+      "sin": 670,
+      "cos": 671,
+      "Ġarc": 672,
+      "scripts": 673,
+      "Ġ..": 674,
+      "deg": 675,
+      "Pr": 676,
+      "Ġprop": 677,
+      "Ġgcd": 678,
+      "eff": 679,
+      "Ġ26": 680,
+      "sans": 681,
+      "Ġ<->": 682,
+      "32": 683,
+      "har": 684,
+      "po": 685,
+      "Ġ28": 686,
+      "quare": 687,
+      "Ġsquare": 688,
+      "Ġballot": 689,
+      "Ġ35": 690,
+      "id": 691,
+      "ad": 692,
+      "cc": 693,
+      "inf": 694,
+      "Ġeq": 695,
+      "en": 696,
+      "her": 697,
+      "Ġ45": 698,
+      "vol": 699,
+      "Ġ<-": 700,
+      "underline": 701,
+      "Ġ100": 702,
+      "25": 703,
+      "diag": 704,
+      "Ġhar": 705,
+      "poon": 706,
+      "Ġharpoon": 707,
+      "24": 708,
+      "pilcrow": 709,
+      "ln": 710,
+      "23": 711,
+      "11": 712,
+      "sc": 713,
+      "Ġ44": 714,
+      "se": 715,
+      "Xi": 716,
+      "iota": 717,
+      "Ġsucc": 718,
+      "Ġarctan": 719,
+      "Ġtack": 720,
+      "67": 721,
+      "99": 722,
+      "Ġ40": 723,
+      "co": 724,
+      "eil": 725,
+      "Ġceil": 726,
+      "Ġcoth": 727,
+      "caron": 728,
+      "Ric": 729,
+      "14": 730,
+      "04": 731,
+      "Ġ02": 732,
+      "Ġsection": 733,
+      "13": 734,
+      "sig": 735,
+      "75": 736,
+      "sign": 737,
+      "64": 738,
+      "Ġ42": 739,
+      "bar": 740,
+      "Ġ72": 741,
+      "Ġ....": 742,
+      "Ġ41": 743,
+      "10": 744,
+      "gn": 745,
+      "60": 746,
+      "ker": 747,
+      "sgn": 748,
+      "28": 749,
+      "ch": 750,
+      "Ġ60": 751,
+      "ev": 752,
+      "84": 753,
+      "Ġ56": 754,
+      "Ġ96": 755,
+      "56": 756,
+      "ph": 757,
+      "Ġ128": 758,
+      "96": 759,
+      "16": 760,
+      "76": 761,
+      "Id": 762,
+      "dist": 763,
+      "20": 764,
+      "80": 765,
+      "ran": 766,
+      "Ġ29": 767,
+      "int": 768,
+      "II": 769,
+      "ok": 770,
+      "hook": 771,
+      "ith": 772,
+      "Vol": 773,
+      "Ġ112": 774,
+      "000": 775,
+      "th": 776,
+      "with": 777,
+      "rad": 778,
+      "Var": 779,
+      "Ġ37": 780,
+      "34": 781,
+      "pan": 782,
+      "55": 783,
+      "cl": 784,
+      "br": 785,
+      "cut": 786,
+      "nd": 787,
+      "Ad": 788,
+      "triangle": 789,
+      "cute": 790,
+      "bracket": 791,
+      "Ġ?": 792,
+      "Res": 793,
+      "ord": 794,
+      "ise": 795,
+      "ym": 796,
+      "...": 797,
+      "Ġ43": 798,
+      "Ġ50": 799,
+      "here": 800,
+      "72": 801,
+      "15": 802,
+      "Upsilon": 803,
+      "wise": 804,
+      "|\"": 805,
+      "other": 806,
+      "Ġ\"|\"": 807,
+      "otherwise": 808,
+      "Ġacute": 809,
+      "94": 810,
+      "Ġ54": 811,
+      "36": 812,
+      "rank": 813,
+      "where": 814,
+      "05": 815,
+      "95": 816,
+      "88": 817,
+      "17": 818,
+      "ac": 819,
+      "ex": 820,
+      "Ġ124": 821,
+      "0000": 822,
+      "Ġ120": 823,
+      "Ġ]'": 824,
+      "eph": 825,
+      "und": 826,
+      "35": 827,
+      "Ġ\\&": 828,
+      "Ġ1234": 829,
+      "Ġ256": 830,
+      "reg": 831,
+      "Ġ49": 832,
+      "arg": 833,
+      "neq": 834,
+      "90": 835,
+      "span": 836,
+      "Ġ134": 837,
+      "Ġtr": 838,
+      "sp": 839,
+      "Ġaleph": 840,
+      "Li": 841,
+      "Ġ51": 842,
+      "NR": 843,
+      "Ġ\\_": 844,
+      "Ġ111": 845,
+      "odd": 846,
+      "21": 847,
+      "33": 848,
+      "74": 849,
+      "italic": 850,
+      "Hom": 851,
+      "even": 852,
+      "86": 853,
+      "Ġ234": 854,
+      "sym": 855,
+      "97": 856,
+      "ur": 857,
+      "YM": 858,
+      "92": 859,
+      "ballot": 860,
+      "44": 861,
+      "85": 862,
+      "01": 863,
+      "Co": 864,
+      "Ġ90": 865,
+      "Ġ<-->": 866,
+      "CP": 867,
+      "at": 868,
+      "Ġmod": 869,
+      "ound": 870,
+      "Ġcsc": 871,
+      "Ġ52": 872,
+      "Ġ55": 873,
+      "MA": 874,
+      "ind": 875,
+      "cosh": 876,
+      "Ġ46": 877,
+      "Ġ47": 878,
+      "Ġ66": 879,
+      "limits": 880,
+      "Ġ67": 881,
+      "supp": 882,
+      "loc": 883,
+      "93": 884,
+      "Br": 885,
+      "Ker": 886,
+      "SI": 887,
+      "lt": 888,
+      "out": 889,
+      "Ind": 890,
+      "Ġsec": 891,
+      "31": 892,
+      "70": 893,
+      "per": 894,
+      "res": 895,
+      "Ġpound": 896,
+      "ix": 897,
+      "Ġ144": 898,
+      "Ġarcsin": 899,
+      "grad": 900,
+      "Ġid": 901,
+      "Ġhom": 902,
+      "68": 903,
+      "ree": 904,
+      "ext": 905,
+      "ly": 906,
+      "Ġ03": 907,
+      "Ġ81": 908,
+      "52": 909,
+      "98": 910,
+      "Ġ57": 911,
+      "Ġ192": 912,
+      "cur": 913,
+      "tri": 914,
+      "Ġ122": 915,
+      "43": 916,
+      "ess": 917,
+      "Ġ125": 918,
+      "02": 919,
+      "Con": 920,
+      "Di": 921,
+      "Ġ135": 922,
+      "Ġarccos": 923,
+      "Ġ80": 924,
+      "78": 925,
+      "wt": 926,
+      "Ġ58": 927,
+      "const": 928,
+      "coh": 929,
+      "Ai": 930,
+      "inv": 931,
+      "45": 932,
+      "RF": 933,
+      "sinh": 934,
+      "FD": 935,
+      "NC": 936,
+      "gh": 937,
+      "Ġ1212": 938,
+      "Ġ102": 939,
+      ".\"": 940,
+      "91": 941,
+      "breve": 942,
+      "exists": 943,
+      "arc": 944,
+      "gcd": 945,
+      "Ġ240": 946,
+      "50": 947,
+      "MC": 948,
+      "Sp": 949,
+      "Ġ200": 950,
+      "Ġ101": 951,
+      "Ġ108": 952,
+      "els": 953,
+      "Ġmodels": 954,
+      "77": 955,
+      "End": 956,
+      "gr": 957,
+      "Ġ432": 958,
+      "Ġ61": 959,
+      "Ġ211": 960,
+      "Ġ145": 961,
+      "30": 962,
+      "48": 963,
+      "Det": 964,
+      "Ex": 965,
+      "ge": 966,
+      "tot": 967,
+      "times": 968,
+      "Ġ000": 969,
+      "divides": 970,
+      "66": 971,
+      "diam": 972,
+      "42": 973,
+      "nc": 974,
+      "Ġ39": 975,
+      "sec": 976,
+      "tx": 977,
+      "Ġ63": 978,
+      "Ġ70": 979,
+      "Ġ78": 980,
+      "Ġ212": 981,
+      "BF": 982,
+      "igg": 983,
+      "Ġ38": 984,
+      "rea": 985,
+      "low": 986,
+      "see": 987,
+      "so": 988,
+      "vac": 989,
+      "65": 990,
+      "GL": 991,
+      "SO": 992,
+      "ne": 993,
+      "Ġ84": 994,
+      "squ": 995,
+      "Ġ121": 996,
+      "curl": 997,
+      "iggly": 998,
+      "squiggly": 999
+    },
+    "merges": [
+      "Ġ )",
+      "Ġ (",
+      "Ġ _",
+      "Ġ ^",
+      "Ġ 1",
+      "Ġ ,",
+      "Ġ -",
+      "Ġ 2",
+      "Ġ =",
+      "Ġ +",
+      "Ġ i",
+      "Ġ d",
+      "Ġ t",
+      "Ġ n",
+      "Ġ x",
+      "Ġ a",
+      "Ġ /",
+      "Ġ s",
+      "Ġ p",
+      "Ġ 0",
+      "t a",
+      "Ġ k",
+      "Ġ m",
+      "Ġ |",
+      "Ġ b",
+      "a l",
+      "Ġ e",
+      "Ġ u",
+      "Ġ l",
+      "Ġ j",
+      "Ġ .",
+      "Ġ c",
+      "Ġ &",
+      "a m",
+      "Ġ o",
+      "Ġ r",
+      "h a",
+      "Ġ g",
+      "e ta",
+      "e g",
+      "Ġ z",
+      "m a",
+      "Ġ \\",
+      "Ġi n",
+      "h i",
+      "Ġ f",
+      "i g",
+      "Ġ y",
+      "i n",
+      "Ġ q",
+      "p ha",
+      "o t",
+      "i l",
+      "Ġa l",
+      "Ġal pha",
+      "Ġ 3",
+      "Ġd ot",
+      "d a",
+      "am b",
+      "amb da",
+      "u m",
+      "e l",
+      "Ġs um",
+      "Ġ v",
+      "Ġ A",
+      "Ġ ]",
+      "al t",
+      "Ġ P",
+      "Ġd i",
+      "Ġm u",
+      "Ġl ambda",
+      "Ġ <",
+      "Ġ [",
+      "Ġp hi",
+      "r al",
+      "d e",
+      "Ġ N",
+      "l e",
+      "Ġ T",
+      "el ta",
+      "am ma",
+      "Ġdi f",
+      "Ġ L",
+      "Ġ D",
+      "Ġ X",
+      "t eg",
+      "teg ral",
+      "i m",
+      "Ġdif f",
+      "Ġ 4",
+      "Ġ h",
+      "e r",
+      "p r",
+      "Ġin tegral",
+      "ig h",
+      "igh t",
+      "pr ight",
+      "in e",
+      "l ine",
+      "eg a",
+      "m ega",
+      "Ġu pright",
+      "Ġ R",
+      "Ġ w",
+      "o n",
+      "Ġ B",
+      "il de",
+      "Ġ G",
+      "v er",
+      "ver line",
+      "Ġb eta",
+      "h eta",
+      "ig ma",
+      "Ġ< =",
+      "Ġ S",
+      "Ġc al",
+      "Ġp i",
+      "Ġo verline",
+      "Ġo o",
+      "p s",
+      "Ġ| |",
+      "Ġdot s",
+      "Ġa n",
+      "Ġ M",
+      "Ġt heta",
+      "Ġ C",
+      "Ġt ilde",
+      "il on",
+      "ps ilon",
+      "Ġ H",
+      "h o",
+      "Ġ *",
+      "Ġg amma",
+      "Ġ F",
+      "Ġ :",
+      "g le",
+      "Ġe psilon",
+      "s i",
+      "Ġs igma",
+      "Ġt a",
+      "Ġx i",
+      "Ġd elta",
+      "Ġta u",
+      "Ġn u",
+      "Ġ E",
+      "o l",
+      "e s",
+      "Ġr ho",
+      "ol d",
+      "Ġan gle",
+      "Ġ >",
+      "Ġ I",
+      "Ġ \"",
+      "Ġb old",
+      "ha t",
+      "Ġo mega",
+      "Ġ O",
+      "Ġ K",
+      "l a",
+      "Ġ V",
+      "Ġe ta",
+      "u s",
+      "Ġp si",
+      "Ġ hat",
+      "r o",
+      "Ġ }",
+      "r t",
+      "q rt",
+      "Ġs qrt",
+      "Ġ {",
+      "im es",
+      "Ġ Q",
+      "Ġt imes",
+      "l l",
+      "Ġe ll",
+      "Ġb b",
+      "Ġ\\ ;",
+      "Ġ U",
+      "a b",
+      "Ġ Y",
+      "ab la",
+      "Ġn abla",
+      "Ġ J",
+      "Ġ Z",
+      "o m",
+      "Ġ W",
+      "r c",
+      "Ġ- >",
+      "ĠD elta",
+      "i rc",
+      "irc le",
+      "Ġ> =",
+      "c t",
+      "c ircle",
+      "o s",
+      "ĠO mega",
+      "ĠG amma",
+      "o g",
+      "Ġ !",
+      "Ġl og",
+      "l us",
+      "ĠP hi",
+      "Ġc hi",
+      "Ġ 5",
+      "d u",
+      "Ġp lus",
+      "ro w",
+      "Ġz eta",
+      "Ġl r",
+      "p a",
+      "a p",
+      "r row",
+      "ap pa",
+      "in us",
+      "Ġa rrow",
+      "Ġ 6",
+      "ĠL ambda",
+      "du ct",
+      "Ġk appa",
+      "Ġp ro",
+      "Ġm a",
+      "Ġpro duct",
+      "m inus",
+      "s t",
+      "om p",
+      "os e",
+      "Ġc omp",
+      "Ġcomp ose",
+      "Ġ ;",
+      "u a",
+      "Ġd el",
+      "Ġdel im",
+      "i de",
+      "ua d",
+      "in om",
+      "Ġq uad",
+      "a s",
+      "Ġb inom",
+      "as es",
+      "c al",
+      "Ġl im",
+      "ĠP si",
+      "r a",
+      "s um",
+      "a n",
+      "Ġ 8",
+      "Ġs u",
+      "Ġs in",
+      "Ġ1 2",
+      "Ġu n",
+      "b s",
+      "Ġc os",
+      "ra k",
+      "Ġ '",
+      "Ġa st",
+      "Ġ\\ {",
+      "Ġ\\ }",
+      "Ġan d",
+      "e t",
+      "x p",
+      "Ġma t",
+      "t s",
+      "Ġs e",
+      "Ġse ct",
+      "Ġf rak",
+      "t ilde",
+      "i v",
+      "Ġe xp",
+      "Ġ\" (",
+      "Ġ\"( \"",
+      "in tegral",
+      "q u",
+      "qu iv",
+      "ral l",
+      "ĠS igma",
+      "Ġp r",
+      "Ġc ases",
+      "l im",
+      "r i",
+      "o rall",
+      "Ġ! =",
+      "im e",
+      "Ġpr ime",
+      "Ġe quiv",
+      "Ġl n",
+      "a g",
+      "Ġw ide",
+      "Ġdi v",
+      "Ġf orall",
+      "ide s",
+      "Ġdiv ides",
+      "g er",
+      "Ġd ag",
+      "Ġdag ger",
+      ". .",
+      "p hi",
+      "Ġ1 1",
+      "an gle",
+      "Ġ 7",
+      "Ġma x",
+      "Ġ) '",
+      "e q",
+      "c k",
+      "r e",
+      "Ġa bs",
+      "i on",
+      "la n",
+      "Ġsu p",
+      "Ġ. ..",
+      "i f",
+      "de r",
+      "der line",
+      "ĠP i",
+      "Ġun ion",
+      "ri p",
+      "ĠT heta",
+      "c rip",
+      "crip ts",
+      "Ġun derline",
+      "| |",
+      "w j",
+      "Ġsu bs",
+      "Ġsubs et",
+      "d if",
+      "Ġs cripts",
+      "c ases",
+      "Ġ 9",
+      "Ġm in",
+      "ta r",
+      "Ġs tar",
+      "dif f",
+      "Ġ1 0",
+      "Ġl t",
+      "Ġz wj",
+      "d o",
+      "i ts",
+      "Ġlim its",
+      "u t",
+      "o verline",
+      "d elta",
+      "i t",
+      "Ġo p",
+      "o r",
+      "an s",
+      "D elta",
+      "e c",
+      "ho ut",
+      "Ġw it",
+      "Ġwit hout",
+      "Ġ\" [",
+      "Ġ\"[ \"",
+      "Ġd et",
+      "u b",
+      "- >",
+      "do ub",
+      "doub le",
+      "Ġs ans",
+      "c e",
+      "er p",
+      "Ġp erp",
+      "b old",
+      "re du",
+      "redu ce",
+      "lan ck",
+      "Ġp lanck",
+      "l ambda",
+      "o p",
+      "al pha",
+      "Ġ1 6",
+      "ps i",
+      "o ta",
+      "Ġin f",
+      "e d",
+      "m u",
+      "k ed",
+      "ro ked",
+      "st roked",
+      "r ho",
+      "Ġo r",
+      "pr o",
+      "Ġi ota",
+      "s igma",
+      "P hi",
+      "Ġ2 2",
+      "Ġ2 1",
+      "Ġ1 3",
+      "g amma",
+      "b b",
+      "a r",
+      "d ot",
+      "Ġ2 4",
+      "or m",
+      "Ġdi m",
+      "o mega",
+      "o d",
+      "l r",
+      "lan t",
+      "s lant",
+      "hi n",
+      "Ġ2 3",
+      "x i",
+      "t heta",
+      "Ġsin h",
+      "Ġv ec",
+      "ri angle",
+      "G amma",
+      "m od",
+      "b eta",
+      "Ġcos h",
+      "ta u",
+      "p i",
+      "Ġt riangle",
+      "n abla",
+      "Ġn orm",
+      "pro x",
+      "Ġt op",
+      "p prox",
+      "Ġa pprox",
+      "ar on",
+      "P si",
+      "u l",
+      "le t",
+      "ul let",
+      "Ġb ullet",
+      "Ġ| ->",
+      "c hi",
+      "Ġm inus",
+      "p lus",
+      "e psilon",
+      "Ġc aron",
+      "ĠR e",
+      "T r",
+      "c row",
+      "il crow",
+      "Ġ1 4",
+      "Ġ- ->",
+      "Ġta n",
+      "L ambda",
+      "Ġ3 2",
+      "Ġd eg",
+      "O mega",
+      "0 0",
+      "i c",
+      "Ġn ot",
+      "ĠX i",
+      "al l",
+      "la s",
+      "n u",
+      "a ck",
+      "s las",
+      "Ġb ack",
+      "slas h",
+      "Ġback slash",
+      "hin g",
+      "Ġnot hing",
+      "s s",
+      "Ġ1 5",
+      "t r",
+      "f rak",
+      "de t",
+      "s q",
+      "Ġ2 0",
+      "= >",
+      "le ss",
+      "Ġg t",
+      "ab s",
+      "Ġp ilcrow",
+      "Ġdot less",
+      "ma t",
+      "z eta",
+      "an d",
+      "{ \"",
+      "Ġ\" {\"",
+      "l ic",
+      "ta lic",
+      "d im",
+      "v ec",
+      "Ġ0 1",
+      "pro duct",
+      "ua re",
+      "u pright",
+      "c on",
+      "n ot",
+      "k appa",
+      "u p",
+      "Ġi talic",
+      "Ġ0 0",
+      "e quiv",
+      "s up",
+      "Ġ= >",
+      "ĠU psilon",
+      "l o",
+      "s m",
+      "re v",
+      "Ġc ot",
+      "sm all",
+      "Ġ2 5",
+      "Ġt hin",
+      "ĠI m",
+      "d iv",
+      "con t",
+      "Ġ1 8",
+      "Ġ3 1",
+      "Ġu psilon",
+      "Ġb ot",
+      "w n",
+      "do wn",
+      "P i",
+      "l og",
+      "S igma",
+      "T heta",
+      "st s",
+      "xi sts",
+      "Ġ3 4",
+      "a rrow",
+      "ma x",
+      "m in",
+      "on g",
+      "l ong",
+      "Ġ3 3",
+      "sq uare",
+      "e xp",
+      "R e",
+      "d i",
+      "ra ck",
+      "lo or",
+      "rack et",
+      "Ġe xists",
+      "Ġk er",
+      "el l",
+      "Ġ<= =>",
+      "Ġf loor",
+      "Ġtan h",
+      "on o",
+      "Ġ2 7",
+      "rall el",
+      "ĠP r",
+      "Ġ12 3",
+      "rev e",
+      "z wj",
+      "Ġ1 7",
+      "u n",
+      "f or",
+      "a rallel",
+      "Ġp arallel",
+      "Ġ= =>",
+      "Ġ4 8",
+      "Ġm ono",
+      "Ġpr ec",
+      "r g",
+      "Ġ<= >",
+      "I m",
+      "Ġ3 6",
+      "f orall",
+      "Ġ1 9",
+      "1 2",
+      "b inom",
+      "ps et",
+      "Ġsu pset",
+      "Ġb reve",
+      "Ġ3 0",
+      "Ġa rg",
+      "Ġc ircle",
+      "Ġb racket",
+      "ta n",
+      "on d",
+      "n orm",
+      "am ond",
+      "Ġdi amond",
+      "s qrt",
+      "c d",
+      "all ot",
+      "Ġ6 4",
+      "f f",
+      "s in",
+      "c os",
+      "Ġa rc",
+      "s cripts",
+      "Ġ. .",
+      "d eg",
+      "P r",
+      "Ġpro p",
+      "Ġg cd",
+      "e ff",
+      "Ġ2 6",
+      "s ans",
+      "Ġ< ->",
+      "3 2",
+      "ha r",
+      "p o",
+      "Ġ2 8",
+      "q uare",
+      "Ġs quare",
+      "Ġb allot",
+      "Ġ3 5",
+      "i d",
+      "a d",
+      "c c",
+      "in f",
+      "Ġe q",
+      "e n",
+      "h er",
+      "Ġ4 5",
+      "v ol",
+      "Ġ< -",
+      "un derline",
+      "Ġ10 0",
+      "2 5",
+      "di ag",
+      "Ġ har",
+      "po on",
+      "Ġhar poon",
+      "2 4",
+      "p ilcrow",
+      "l n",
+      "2 3",
+      "1 1",
+      "s c",
+      "Ġ4 4",
+      "s e",
+      "X i",
+      "i ota",
+      "Ġsu cc",
+      "Ġarc tan",
+      "Ġta ck",
+      "6 7",
+      "9 9",
+      "Ġ4 0",
+      "c o",
+      "e il",
+      "Ġc eil",
+      "Ġcot h",
+      "c aron",
+      "R ic",
+      "1 4",
+      "0 4",
+      "Ġ0 2",
+      "Ġsect ion",
+      "1 3",
+      "s ig",
+      "7 5",
+      "sig n",
+      "6 4",
+      "Ġ4 2",
+      "b ar",
+      "Ġ7 2",
+      "Ġ... .",
+      "Ġ4 1",
+      "1 0",
+      "g n",
+      "6 0",
+      "k er",
+      "s gn",
+      "2 8",
+      "c h",
+      "Ġ6 0",
+      "e v",
+      "8 4",
+      "Ġ5 6",
+      "Ġ9 6",
+      "5 6",
+      "p h",
+      "Ġ12 8",
+      "9 6",
+      "1 6",
+      "7 6",
+      "I d",
+      "di st",
+      "2 0",
+      "8 0",
+      "ra n",
+      "Ġ2 9",
+      "in t",
+      "I I",
+      "o k",
+      "ho ok",
+      "it h",
+      "V ol",
+      "Ġ11 2",
+      "00 0",
+      "t h",
+      "w ith",
+      "ra d",
+      "V ar",
+      "Ġ3 7",
+      "3 4",
+      "pa n",
+      "5 5",
+      "c l",
+      "b r",
+      "c ut",
+      "n d",
+      "A d",
+      "t riangle",
+      "cut e",
+      "b racket",
+      "Ġ ?",
+      "R es",
+      "or d",
+      "i se",
+      "y m",
+      ".. .",
+      "Ġ4 3",
+      "Ġ5 0",
+      "her e",
+      "7 2",
+      "1 5",
+      "U psilon",
+      "w ise",
+      "| \"",
+      "ot her",
+      "Ġ\" |\"",
+      "other wise",
+      "Ġa cute",
+      "9 4",
+      "Ġ5 4",
+      "3 6",
+      "ran k",
+      "w here",
+      "0 5",
+      "9 5",
+      "8 8",
+      "1 7",
+      "a c",
+      "e x",
+      "Ġ12 4",
+      "00 00",
+      "Ġ12 0",
+      "Ġ] '",
+      "e ph",
+      "un d",
+      "3 5",
+      "Ġ\\ &",
+      "Ġ123 4",
+      "Ġ25 6",
+      "r eg",
+      "Ġ4 9",
+      "ar g",
+      "n eq",
+      "9 0",
+      "s pan",
+      "Ġ13 4",
+      "Ġt r",
+      "s p",
+      "Ġal eph",
+      "L i",
+      "Ġ5 1",
+      "N R",
+      "Ġ\\ _",
+      "Ġ11 1",
+      "od d",
+      "2 1",
+      "3 3",
+      "7 4",
+      "i talic",
+      "H om",
+      "ev en",
+      "8 6",
+      "Ġ23 4",
+      "s ym",
+      "9 7",
+      "u r",
+      "Y M",
+      "9 2",
+      "b allot",
+      "4 4",
+      "8 5",
+      "0 1",
+      "C o",
+      "Ġ9 0",
+      "Ġ<- ->",
+      "C P",
+      "a t",
+      "Ġm od",
+      "o und",
+      "Ġc sc",
+      "Ġ5 2",
+      "Ġ5 5",
+      "M A",
+      "in d",
+      "cos h",
+      "Ġ4 6",
+      "Ġ4 7",
+      "Ġ6 6",
+      "lim its",
+      "Ġ6 7",
+      "sup p",
+      "lo c",
+      "9 3",
+      "B r",
+      "K er",
+      "S I",
+      "l t",
+      "o ut",
+      "I nd",
+      "Ġse c",
+      "3 1",
+      "7 0",
+      "p er",
+      "r es",
+      "Ġp ound",
+      "i x",
+      "Ġ14 4",
+      "Ġarc sin",
+      "g rad",
+      "Ġi d",
+      "Ġh om",
+      "6 8",
+      "re e",
+      "ex t",
+      "l y",
+      "Ġ0 3",
+      "Ġ8 1",
+      "5 2",
+      "9 8",
+      "Ġ5 7",
+      "Ġ19 2",
+      "c ur",
+      "t ri",
+      "Ġ12 2",
+      "4 3",
+      "es s",
+      "Ġ12 5",
+      "0 2",
+      "C on",
+      "D i",
+      "Ġ13 5",
+      "Ġarc cos",
+      "Ġ8 0",
+      "7 8",
+      "w t",
+      "Ġ5 8",
+      "con st",
+      "co h",
+      "A i",
+      "in v",
+      "4 5",
+      "R F",
+      "sin h",
+      "F D",
+      "N C",
+      "g h",
+      "Ġ12 12",
+      "Ġ10 2",
+      ". \"",
+      "9 1",
+      "b reve",
+      "e xists",
+      "a rc",
+      "g cd",
+      "Ġ24 0",
+      "5 0",
+      "M C",
+      "S p",
+      "Ġ2 00",
+      "Ġ10 1",
+      "Ġ10 8",
+      "el s",
+      "Ġmod els",
+      "7 7",
+      "E nd",
+      "g r",
+      "Ġ4 32",
+      "Ġ6 1",
+      "Ġ21 1",
+      "Ġ14 5",
+      "3 0",
+      "4 8",
+      "D et",
+      "E x",
+      "g e",
+      "t ot",
+      "t imes",
+      "Ġ0 00",
+      "div ides",
+      "6 6",
+      "di am",
+      "4 2",
+      "n c",
+      "Ġ3 9",
+      "s ec",
+      "t x",
+      "Ġ6 3",
+      "Ġ7 0",
+      "Ġ7 8",
+      "Ġ21 2",
+      "B F",
+      "ig g",
+      "Ġ3 8",
+      "re a",
+      "lo w",
+      "se e",
+      "s o",
+      "v ac",
+      "6 5",
+      "G L",
+      "S O",
+      "n e",
+      "Ġ8 4",
+      "s qu",
+      "Ġ12 1",
+      "cur l",
+      "igg ly",
+      "squ iggly"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "TrOCRProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}