clean

config.json

@@ -1,44 +0,0 @@
-{
-  "_name_or_path": "hf-internal-testing/tiny-random-BertModel",
-  "architectures": [
-    "BertModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 32,
-  "initializer_range": 0.02,
-  "intermediate_size": 37,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "neuron": {
-    "auto_cast": null,
-    "auto_cast_type": null,
-    "compiler_type": "neuronx-cc",
-    "compiler_version": "2.8.0.25+a3ad0f342",
-    "disable_fallback": false,
-    "disable_fast_relayout": false,
-    "dynamic_batch_size": false,
-    "input_names": [
-      "input_ids",
-      "attention_mask",
-      "token_type_ids"
-    ],
-    "output_names": [
-      "logits"
-    ],
-    "static_batch_size": 1,
-    "static_sequence_length": 32
-  },
-  "num_attention_heads": 4,
-  "num_hidden_layers": 5,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
-  "type_vocab_size": 16,
-  "use_cache": true,
-  "vocab_size": 1124
-}

feature_extractor/preprocessor_config.json

@@ -1,28 +0,0 @@
-{
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_processor_type": "CLIPImageProcessor",
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 224
-  }
-}

model_index.json

@@ -1,32 +0,0 @@
-{
-  "_class_name": "NeuronStableDiffusionPipeline",
-  "_diffusers_version": "0.19.3",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "PNDMScheduler"
-  ],
-  "text_encoder": [
-    "optimum",
-    "NeuronModelTextEncoder"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "optimum",
-    "NeuronModelUnet"
-  ],
-  "vae_decoder": [
-    "optimum",
-    "NeuronModelVaeDecoder"
-  ]
-}

scheduler/scheduler_config.json

@@ -1,15 +0,0 @@
-{
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.19.3",
-  "beta_end": 0.012,
-  "beta_schedule": "scaled_linear",
-  "beta_start": 0.00085,
-  "clip_sample": false,
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "set_alpha_to_one": false,
-  "skip_prk_steps": true,
-  "steps_offset": 1,
-  "timestep_spacing": "leading",
-  "trained_betas": null
-}

special_tokens_map.json

@@ -1,7 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}

text_encoder/config.json

@@ -1,45 +0,0 @@
-{
-  "_commit_hash": "a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d",
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-torch/snapshots/a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d/text_encoder",
-  "architectures": [
-    "CLIPTextModel"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "dropout": 0.0,
-  "eos_token_id": 2,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 32,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 37,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 77,
-  "model_type": "clip-text-model",
-  "neuron": {
-    "auto_cast": null,
-    "auto_cast_type": null,
-    "compiler_type": "neuronx-cc",
-    "compiler_version": "2.8.0.25+a3ad0f342",
-    "disable_fallback": false,
-    "disable_fast_relayout": false,
-    "dynamic_batch_size": false,
-    "input_names": [
-      "input_ids"
-    ],
-    "output_names": [
-      "text_embeds",
-      "last_hidden_state"
-    ],
-    "static_batch_size": 1,
-    "static_sequence_length": 77
-  },
-  "num_attention_heads": 4,
-  "num_hidden_layers": 5,
-  "pad_token_id": 1,
-  "projection_dim": 512,
-  "torch_dtype": "float32",
-  "torchscript": true,
-  "transformers_version": "4.22.2",
-  "vocab_size": 1000
-}

tokenizer.json

@@ -1,1274 +0,0 @@
-{
-  "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": "[UNK]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 2,
-      "content": "[CLS]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 3,
-      "content": "[SEP]",
-      "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
-    }
-  ],
-  "normalizer": {
-    "type": "BertNormalizer",
-    "clean_text": true,
-    "handle_chinese_chars": true,
-    "strip_accents": null,
-    "lowercase": true
-  },
-  "pre_tokenizer": {
-    "type": "BertPreTokenizer"
-  },
-  "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "[CLS]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "[CLS]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "[SEP]",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {
-      "[CLS]": {
-        "id": "[CLS]",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "[CLS]"
-        ]
-      },
-      "[SEP]": {
-        "id": "[SEP]",
-        "ids": [
-          3
-        ],
-        "tokens": [
-          "[SEP]"
-        ]
-      }
-    }
-  },
-  "decoder": {
-    "type": "WordPiece",
-    "prefix": "##",
-    "cleanup": true
-  },
-  "model": {
-    "type": "WordPiece",
-    "unk_token": "[UNK]",
-    "continuing_subword_prefix": "##",
-    "max_input_chars_per_word": 100,
-    "vocab": {
-      "[PAD]": 0,
-      "[UNK]": 1,
-      "[CLS]": 2,
-      "[SEP]": 3,
-      "[MASK]": 4,
-      "!": 5,
-      "\"": 6,
-      "#": 7,
-      "$": 8,
-      "%": 9,
-      "&": 10,
-      "'": 11,
-      "(": 12,
-      ")": 13,
-      "*": 14,
-      "+": 15,
-      ",": 16,
-      "-": 17,
-      ".": 18,
-      "/": 19,
-      "0": 20,
-      "1": 21,
-      "2": 22,
-      "3": 23,
-      "4": 24,
-      "5": 25,
-      "6": 26,
-      "7": 27,
-      "8": 28,
-      "9": 29,
-      ":": 30,
-      ";": 31,
-      "<": 32,
-      "=": 33,
-      ">": 34,
-      "?": 35,
-      "@": 36,
-      "[": 37,
-      "\\": 38,
-      "]": 39,
-      "^": 40,
-      "_": 41,
-      "`": 42,
-      "a": 43,
-      "b": 44,
-      "c": 45,
-      "d": 46,
-      "e": 47,
-      "f": 48,
-      "g": 49,
-      "h": 50,
-      "i": 51,
-      "j": 52,
-      "k": 53,
-      "l": 54,
-      "m": 55,
-      "n": 56,
-      "o": 57,
-      "p": 58,
-      "q": 59,
-      "r": 60,
-      "s": 61,
-      "t": 62,
-      "u": 63,
-      "v": 64,
-      "w": 65,
-      "x": 66,
-      "y": 67,
-      "z": 68,
-      "|": 69,
-      "}": 70,
-      "~": 71,
-      "¡": 72,
-      "¢": 73,
-      "£": 74,
-      "¥": 75,
-      "§": 76,
-      "°": 77,
-      "±": 78,
-      "²": 79,
-      "³": 80,
-      "´": 81,
-      "µ": 82,
-      "·": 83,
-      "º": 84,
-      "½": 85,
-      "¿": 86,
-      "×": 87,
-      "ß": 88,
-      "æ": 89,
-      "ð": 90,
-      "ø": 91,
-      "þ": 92,
-      "đ": 93,
-      "ħ": 94,
-      "ı": 95,
-      "ł": 96,
-      "œ": 97,
-      "ɐ": 98,
-      "ɑ": 99,
-      "ɒ": 100,
-      "ɔ": 101,
-      "ə": 102,
-      "ɛ": 103,
-      "ɜ": 104,
-      "ɡ": 105,
-      "ɢ": 106,
-      "ɪ": 107,
-      "ɫ": 108,
-      "ɳ": 109,
-      "ɽ": 110,
-      "ɾ": 111,
-      "ʁ": 112,
-      "ʃ": 113,
-      "ʊ": 114,
-      "ʋ": 115,
-      "ʒ": 116,
-      "ʔ": 117,
-      "ʕ": 118,
-      "ʲ": 119,
-      "ʻ": 120,
-      "ʼ": 121,
-      "ʾ": 122,
-      "ʿ": 123,
-      "ˈ": 124,
-      "ˌ": 125,
-      "ː": 126,
-      "α": 127,
-      "β": 128,
-      "γ": 129,
-      "δ": 130,
-      "ε": 131,
-      "η": 132,
-      "θ": 133,
-      "ι": 134,
-      "κ": 135,
-      "λ": 136,
-      "μ": 137,
-      "��": 138,
-      "ξ": 139,
-      "ο": 140,
-      "π": 141,
-      "ρ": 142,
-      "ς": 143,
-      "σ": 144,
-      "τ": 145,
-      "υ": 146,
-      "φ": 147,
-      "χ": 148,
-      "ψ": 149,
-      "ω": 150,
-      "а": 151,
-      "б": 152,
-      "в": 153,
-      "г": 154,
-      "д": 155,
-      "е": 156,
-      "ж": 157,
-      "з": 158,
-      "и": 159,
-      "к": 160,
-      "л": 161,
-      "м": 162,
-      "н": 163,
-      "о": 164,
-      "п": 165,
-      "р": 166,
-      "с": 167,
-      "т": 168,
-      "у": 169,
-      "х": 170,
-      "ц": 171,
-      "ш": 172,
-      "ъ": 173,
-      "ы": 174,
-      "ь": 175,
-      "ю": 176,
-      "я": 177,
-      "є": 178,
-      "א": 179,
-      "ב": 180,
-      "ג": 181,
-      "ה": 182,
-      "ו": 183,
-      "ז": 184,
-      "ח": 185,
-      "י": 186,
-      "ל": 187,
-      "ם": 188,
-      "מ": 189,
-      "ן": 190,
-      "נ": 191,
-      "ס": 192,
-      "ף": 193,
-      "פ": 194,
-      "צ": 195,
-      "ר": 196,
-      "ש": 197,
-      "ת": 198,
-      "ء": 199,
-      "ا": 200,
-      "ب": 201,
-      "ة": 202,
-      "ت": 203,
-      "ث": 204,
-      "ج": 205,
-      "ح": 206,
-      "خ": 207,
-      "د": 208,
-      "ذ": 209,
-      "ر": 210,
-      "س": 211,
-      "ش": 212,
-      "ص": 213,
-      "ع": 214,
-      "ف": 215,
-      "ق": 216,
-      "ك": 217,
-      "ل": 218,
-      "م": 219,
-      "ن": 220,
-      "ه": 221,
-      "و": 222,
-      "ي": 223,
-      "ܐ": 224,
-      "ܕ": 225,
-      "ܗ": 226,
-      "ܝ": 227,
-      "ܠ": 228,
-      "ܢ": 229,
-      "ܬ": 230,
-      "अ": 231,
-      "ई": 232,
-      "क": 233,
-      "ग": 234,
-      "ण": 235,
-      "त": 236,
-      "द": 237,
-      "न": 238,
-      "प": 239,
-      "ब": 240,
-      "म": 241,
-      "य": 242,
-      "र": 243,
-      "ल": 244,
-      "व": 245,
-      "स": 246,
-      "ह": 247,
-      "ा": 248,
-      "ि": 249,
-      "আ": 250,
-      "ল": 251,
-      "হ": 252,
-      "া": 253,
-      "ਅ": 254,
-      "ਲ": 255,
-      "ਹ": 256,
-      "ਾ": 257,
-      "അ": 258,
-      "ള": 259,
-      "ഹ": 260,
-      "ാ": 261,
-      "ก": 262,
-      "ค": 263,
-      "ง": 264,
-      "ช": 265,
-      "ซ": 266,
-      "ญ": 267,
-      "ฐ": 268,
-      "ณ": 269,
-      "ด": 270,
-      "ต": 271,
-      "น": 272,
-      "บ": 273,
-      "ป": 274,
-      "พ": 275,
-      "ภ": 276,
-      "ม": 277,
-      "ย": 278,
-      "ร": 279,
-      "ล": 280,
-      "ว": 281,
-      "ศ": 282,
-      "ษ": 283,
-      "ส": 284,
-      "ห": 285,
-      "อ": 286,
-      "ฮ": 287,
-      "ะ": 288,
-      "า": 289,
-      "เ": 290,
-      "แ": 291,
-      "ไ": 292,
-      "ა": 293,
-      "ბ": 294,
-      "გ": 295,
-      "დ": 296,
-      "ე": 297,
-      "ვ": 298,
-      "ზ": 299,
-      "თ": 300,
-      "ი": 301,
-      "კ": 302,
-      "ლ": 303,
-      "მ": 304,
-      "ნ": 305,
-      "ო": 306,
-      "პ": 307,
-      "ჟ": 308,
-      "რ": 309,
-      "ს": 310,
-      "ტ": 311,
-      "უ": 312,
-      "ფ": 313,
-      "ქ": 314,
-      "ღ": 315,
-      "ყ": 316,
-      "შ": 317,
-      "ჩ": 318,
-      "ც": 319,
-      "ძ": 320,
-      "წ": 321,
-      "ჭ": 322,
-      "ხ": 323,
-      "ჯ": 324,
-      "ჰ": 325,
-      "ჱ": 326,
-      "ჲ": 327,
-      "ჳ": 328,
-      "ჴ": 329,
-      "ჵ": 330,
-      "ჶ": 331,
-      "ჷ": 332,
-      "ჸ": 333,
-      "ჹ": 334,
-      "ჺ": 335,
-      "჻": 336,
-      "ᄃ": 337,
-      "ᄅ": 338,
-      "ᄇ": 339,
-      "ᄋ": 340,
-      "ᄌ": 341,
-      "ᅡ": 342,
-      "ᅢ": 343,
-      "ᅦ": 344,
-      "ᅧ": 345,
-      "ᅩ": 346,
-      "ᅮ": 347,
-      "ᅵ": 348,
-      "ᆨ": 349,
-      "ᆫ": 350,
-      "ᆯ": 351,
-      "ᆸ": 352,
-      "ᆼ": 353,
-      "ᵻ": 354,
-      "‐": 355,
-      "‑": 356,
-      "–": 357,
-      "—": 358,
-      "―": 359,
-      "‘": 360,
-      "’": 361,
-      "“": 362,
-      "”": 363,
-      "„": 364,
-      "†": 365,
-      "‡": 366,
-      "•": 367,
-      "…": 368,
-      "′": 369,
-      "″": 370,
-      "⁄": 371,
-      "₣": 372,
-      "₤": 373,
-      "€": 374,
-      "₹": 375,
-      "⅓": 376,
-      "⅔": 377,
-      "→": 378,
-      "−": 379,
-      "≡": 380,
-      "≤": 381,
-      "①": 382,
-      "☉": 383,
-      "☫": 384,
-      "♀": 385,
-      "♭": 386,
-      "♯": 387,
-      "⚳": 388,
-      "ⴀ": 389,
-      "ⴂ": 390,
-      "ⴃ": 391,
-      "ⴈ": 392,
-      "ⴌ": 393,
-      "ⴕ": 394,
-      "ⴟ": 395,
-      "〈": 396,
-      "〉": 397,
-      "〜": 398,
-      "あ": 399,
-      "い": 400,
-      "う": 401,
-      "お": 402,
-      "か": 403,
-      "き": 404,
-      "く": 405,
-      "け": 406,
-      "こ": 407,
-      "さ": 408,
-      "し": 409,
-      "す": 410,
-      "せ": 411,
-      "た": 412,
-      "ち": 413,
-      "っ": 414,
-      "つ": 415,
-      "と": 416,
-      "な": 417,
-      "に": 418,
-      "の": 419,
-      "は": 420,
-      "ひ": 421,
-      "ふ": 422,
-      "ほ": 423,
-      "ま": 424,
-      "み": 425,
-      "め": 426,
-      "も": 427,
-      "ゃ": 428,
-      "ゆ": 429,
-      "ょ": 430,
-      "ら": 431,
-      "り": 432,
-      "る": 433,
-      "れ": 434,
-      "わ": 435,
-      "を": 436,
-      "ん": 437,
-      "ァ": 438,
-      "ア": 439,
-      "ィ": 440,
-      "イ": 441,
-      "ゥ": 442,
-      "ウ": 443,
-      "ェ": 444,
-      "エ": 445,
-      "ォ": 446,
-      "オ": 447,
-      "カ": 448,
-      "キ": 449,
-      "ク": 450,
-      "ケ": 451,
-      "コ": 452,
-      "サ": 453,
-      "シ": 454,
-      "ス": 455,
-      "セ": 456,
-      "タ": 457,
-      "チ": 458,
-      "ッ": 459,
-      "ツ": 460,
-      "テ": 461,
-      "ト": 462,
-      "ナ": 463,
-      "ニ": 464,
-      "ネ": 465,
-      "ノ": 466,
-      "ハ": 467,
-      "フ": 468,
-      "ヘ": 469,
-      "マ": 470,
-      "ミ": 471,
-      "ム": 472,
-      "モ": 473,
-      "ャ": 474,
-      "ュ": 475,
-      "ョ": 476,
-      "ラ": 477,
-      "リ": 478,
-      "ル": 479,
-      "レ": 480,
-      "ロ": 481,
-      "ン": 482,
-      "・": 483,
-      "ー": 484,
-      "一": 485,
-      "七": 486,
-      "下": 487,
-      "世": 488,
-      "丙": 489,
-      "中": 490,
-      "主": 491,
-      "乃": 492,
-      "之": 493,
-      "乙": 494,
-      "九": 495,
-      "二": 496,
-      "云": 497,
-      "人": 498,
-      "今": 499,
-      "付": 500,
-      "作": 501,
-      "侗": 502,
-      "依": 503,
-      "信": 504,
-      "傳": 505,
-      "儚": 506,
-      "充": 507,
-      "光": 508,
-      "全": 509,
-      "兵": 510,
-      "其": 511,
-      "具": 512,
-      "円": 513,
-      "再": 514,
-      "出": 515,
-      "判": 516,
-      "前": 517,
-      "剛": 518,
-      "劇": 519,
-      "劉": 520,
-      "動": 521,
-      "化": 522,
-      "北": 523,
-      "华": 524,
-      "厂": 525,
-      "去": 526,
-      "古": 527,
-      "可": 528,
-      "台": 529,
-      "史": 530,
-      "同": 531,
-      "名": 532,
-      "君": 533,
-      "吳": 534,
-      "周": 535,
-      "命": 536,
-      "和": 537,
-      "咲": 538,
-      "善": 539,
-      "四": 540,
-      "國": 541,
-      "園": 542,
-      "圣": 543,
-      "在": 544,
-      "坂": 545,
-      "堤": 546,
-      "場": 547,
-      "塘": 548,
-      "夕": 549,
-      "大": 550,
-      "天": 551,
-      "夫": 552,
-      "女": 553,
-      "妙": 554,
-      "姚": 555,
-      "子": 556,
-      "孟": 557,
-      "守": 558,
-      "安": 559,
-      "宋": 560,
-      "完": 561,
-      "宗": 562,
-      "宝": 563,
-      "宫": 564,
-      "寝": 565,
-      "寺": 566,
-      "小": 567,
-      "少": 568,
-      "尾": 569,
-      "山": 570,
-      "岳": 571,
-      "川": 572,
-      "州": 573,
-      "巳": 574,
-      "市": 575,
-      "師": 576,
-      "平": 577,
-      "广": 578,
-      "庆": 579,
-      "府": 580,
-      "座": 581,
-      "廬": 582,
-      "建": 583,
-      "式": 584,
-      "張": 585,
-      "彌": 586,
-      "彩": 587,
-      "彼": 588,
-      "後": 589,
-      "御": 590,
-      "德": 591,
-      "思": 592,
-      "愛": 593,
-      "憑": 594,
-      "憶": 595,
-      "應": 596,
-      "懷": 597,
-      "战": 598,
-      "戦": 599,
-      "扈": 600,
-      "技": 601,
-      "拉": 602,
-      "拳": 603,
-      "挑": 604,
-      "揺": 605,
-      "攻": 606,
-      "放": 607,
-      "政": 608,
-      "散": 609,
-      "斯": 610,
-      "方": 611,
-      "日": 612,
-      "旦": 613,
-      "旭": 614,
-      "昌": 615,
-      "明": 616,
-      "星": 617,
-      "春": 618,
-      "晋": 619,
-      "景": 620,
-      "曦": 621,
-      "月": 622,
-      "望": 623,
-      "未": 624,
-      "本": 625,
-      "李": 626,
-      "村": 627,
-      "杜": 628,
-      "束": 629,
-      "来": 630,
-      "林": 631,
-      "桜": 632,
-      "梶": 633,
-      "棘": 634,
-      "椎": 635,
-      "楊": 636,
-      "楚": 637,
-      "榮": 638,
-      "橘": 639,
-      "機": 640,
-      "正": 641,
-      "殻": 642,
-      "殿": 643,
-      "母": 644,
-      "水": 645,
-      "汉": 646,
-      "沂": 647,
-      "沙": 648,
-      "河": 649,
-      "泗": 650,
-      "波": 651,
-      "泣": 652,
-      "洪": 653,
-      "淹": 654,
-      "清": 655,
-      "湯": 656,
-      "漢": 657,
-      "澄": 658,
-      "澤": 659,
-      "火": 660,
-      "灯": 661,
-      "灵": 662,
-      "灼": 663,
-      "焼": 664,
-      "熱": 665,
-      "物": 666,
-      "狐": 667,
-      "狸": 668,
-      "玄": 669,
-      "王": 670,
-      "玩": 671,
-      "珂": 672,
-      "珙": 673,
-      "球": 674,
-      "理": 675,
-      "琦": 676,
-      "琪": 677,
-      "瓊": 678,
-      "生": 679,
-      "田": 680,
-      "畢": 681,
-      "番": 682,
-      "瘡": 683,
-      "白": 684,
-      "皮": 685,
-      "真": 686,
-      "砲": 687,
-      "礮": 688,
-      "祈": 689,
-      "神": 690,
-      "祠": 691,
-      "秋": 692,
-      "空": 693,
-      "立": 694,
-      "精": 695,
-      "約": 696,
-      "絵": 697,
-      "織": 698,
-      "義": 699,
-      "翠": 700,
-      "者": 701,
-      "耕": 702,
-      "肖": 703,
-      "胡": 704,
-      "膀": 705,
-      "臂": 706,
-      "興": 707,
-      "良": 708,
-      "花": 709,
-      "芳": 710,
-      "芽": 711,
-      "若": 712,
-      "英": 713,
-      "藕": 714,
-      "藥": 715,
-      "蘄": 716,
-      "蘇": 717,
-      "行": 718,
-      "裁": 719,
-      "規": 720,
-      "覺": 721,
-      "观": 722,
-      "解": 723,
-      "記": 724,
-      "誓": 725,
-      "誡": 726,
-      "誰": 727,
-      "謎": 728,
-      "许": 729,
-      "谭": 730,
-      "豪": 731,
-      "豫": 732,
-      "費": 733,
-      "贵": 734,
-      "赤": 735,
-      "趙": 736,
-      "足": 737,
-      "跡": 738,
-      "転": 739,
-      "辛": 740,
-      "逆": 741,
-      "遇": 742,
-      "運": 743,
-      "過": 744,
-      "遠": 745,
-      "選": 746,
-      "邦": 747,
-      "邱": 748,
-      "部": 749,
-      "郭": 750,
-      "都": 751,
-      "酈": 752,
-      "里": 753,
-      "野": 754,
-      "金": 755,
-      "銃": 756,
-      "鋼": 757,
-      "錄": 758,
-      "錡": 759,
-      "鍵": 760,
-      "鐵": 761,
-      "钱": 762,
-      "铁": 763,
-      "關": 764,
-      "防": 765,
-      "阿": 766,
-      "陈": 767,
-      "陳": 768,
-      "陽": 769,
-      "隊": 770,
-      "階": 771,
-      "集": 772,
-      "雪": 773,
-      "雲": 774,
-      "霖": 775,
-      "霹": 776,
-      "靂": 777,
-      "韓": 778,
-      "願": 779,
-      "顯": 780,
-      "颜": 781,
-      "马": 782,
-      "高": 783,
-      "龍": 784,
-      "ﷲ": 785,
-      "ﻋ": 786,
-      "／": 787,
-      "３": 788,
-      "～": 789,
-      "##i": 790,
-      "##y": 791,
-      "##o": 792,
-      "##r": 793,
-      "##g": 794,
-      "##a": 795,
-      "##w": 796,
-      "##l": 797,
-      "##b": 798,
-      "##z": 799,
-      "##t": 800,
-      "##n": 801,
-      "##c": 802,
-      "##h": 803,
-      "##s": 804,
-      "##u": 805,
-      "##d": 806,
-      "##e": 807,
-      "##k": 808,
-      "##v": 809,
-      "##f": 810,
-      "##x": 811,
-      "##q": 812,
-      "##p": 813,
-      "##æ": 814,
-      "##0": 815,
-      "##5": 816,
-      "##m": 817,
-      "##8": 818,
-      "##4": 819,
-      "##س": 820,
-      "##ت": 821,
-      "##ا": 822,
-      "##ن": 823,
-      "##6": 824,
-      "##1": 825,
-      "##7": 826,
-      "##j": 827,
-      "##つ": 828,
-      "##う": 829,
-      "##2": 830,
-      "##9": 831,
-      "##3": 832,
-      "##ø": 833,
-      "##ล": 834,
-      "##ว": 835,
-      "##ง": 836,
-      "##พ": 837,
-      "##ไ": 838,
-      "##ช": 839,
-      "##ย": 840,
-      "##า": 841,
-      "##ร": 842,
-      "##თ": 843,
-      "##ა": 844,
-      "##ვ": 845,
-      "##რ": 846,
-      "##ი": 847,
-      "##ള": 848,
-      "##あ": 849,
-      "##ん": 850,
-      "##α": 851,
-      "##ν": 852,
-      "##τ": 853,
-      "##ο": 854,
-      "##κ": 855,
-      "##ρ": 856,
-      "##ω": 857,
-      "##ς": 858,
-      "##の": 859,
-      "##な": 860,
-      "##ら": 861,
-      "##ð": 862,
-      "##œ": 863,
-      "##ɛ": 864,
-      "##ł": 865,
-      "##η": 866,
-      "##μ": 867,
-      "##ซ": 868,
-      "##ル": 869,
-      "##シ": 870,
-      "##ア": 871,
-      "##リ": 872,
-      "##ス": 873,
-      "##ʔ": 874,
-      "##ल": 875,
-      "##ᄇ": 876,
-      "##ᅮ": 877,
-      "##ᄃ": 878,
-      "##ᅢ": 879,
-      "##β": 880,
-      "##ß": 881,
-      "##か": 882,
-      "##た": 883,
-      "##ə": 884,
-      "##ʻ": 885,
-      "##ι": 886,
-      "##χ": 887,
-      "##о": 888,
-      "##л": 889,
-      "##с": 890,
-      "##а": 891,
-      "##т": 892,
-      "##ы": 893,
-      "##и": 894,
-      "##в": 895,
-      "##к": 896,
-      "##з": 897,
-      "##ッ": 898,
-      "##ク": 899,
-      "##マ": 900,
-      "##ン": 901,
-      "##გ": 902,
-      "##ლ": 903,
-      "##ო": 904,
-      "##ნ": 905,
-      "##ː": 906,
-      "##ל": 907,
-      "##ה": 908,
-      "##א": 909,
-      "##く": 910,
-      "##み": 911,
-      "##ε": 912,
-      "##ξ": 913,
-      "##ল": 914,
-      "##ˈ": 915,
-      "##ɡ": 916,
-      "##ɑ": 917,
-      "##ɒ": 918,
-      "##し": 919,
-      "##す": 920,
-      "##き": 921,
-      "##ひ": 922,
-      "##と": 923,
-      "##đ": 924,
-      "##ъ": 925,
-      "##н": 926,
-      "##е": 927,
-      "##י": 928,
-      "##פ": 929,
-      "##イ": 930,
-      "##λ": 931,
-      "##ق": 932,
-      "##ع": 933,
-      "##د": 934,
-      "##ᅡ": 935,
-      "##ᆯ": 936,
-      "##ᄅ": 937,
-      "##ɪ": 938,
-      "##ค": 939,
-      "##ต": 940,
-      "##व": 941,
-      "##��": 942,
-      "##द": 943,
-      "##は": 944,
-      "##り": 945,
-      "##レ": 946,
-      "##ー": 947,
-      "##ツ": 948,
-      "##ي": 949,
-      "##ش": 950,
-      "##و": 951,
-      "##م": 952,
-      "##º": 953,
-      "##ਲ": 954,
-      "##ਾ": 955,
-      "##ਹ": 956,
-      "##д": 957,
-      "##р": 958,
-      "##ل": 959,
-      "##ب": 960,
-      "##い": 961,
-      "##ち": 962,
-      "##ゃ": 963,
-      "##ʒ": 964,
-      "##ʃ": 965,
-      "##ɔ": 966,
-      "##ह": 967,
-      "##ニ": 968,
-      "##ウ": 969,
-      "##ァ": 970,
-      "##キ": 971,
-      "##ュ": 972,
-      "##３": 973,
-      "##ხ": 974,
-      "##ს": 975,
-      "##お": 976,
-      "##タ": 977,
-      "##ാ": 978,
-      "##ഹ": 979,
-      "##ɳ": 980,
-      "##ま": 981,
-      "##る": 982,
-      "##ะ": 983,
-      "##อ": 984,
-      "##น": 985,
-      "##ן": 986,
-      "##я": 987,
-      "##แ": 988,
-      "##ก": 989,
-      "##ɾ": 990,
-      "##ʲ": 991,
-      "##フ": 992,
-      "##უ": 993,
-      "##ภ": 994,
-      "##ด": 995,
-      "##ב": 996,
-      "##ת": 997,
-      "##خ": 998,
-      "##ラ": 999,
-      "##れ": 1000,
-      "##ण": 1001,
-      "##स": 1002,
-      "##न": 1003,
-      "##ه": 1004,
-      "##ف": 1005,
-      "##ر": 1006,
-      "##エ": 1007,
-      "##テ": 1008,
-      "##ษ": 1009,
-      "##ฐ": 1010,
-      "##ィ": 1011,
-      "##क": 1012,
-      "##ノ": 1013,
-      "##θ": 1014,
-      "##ネ": 1015,
-      "##ョ": 1016,
-      "##δ": 1017,
-      "##ɽ": 1018,
-      "##ʁ": 1019,
-      "##ტ": 1020,
-      "##ჱ": 1021,
-      "##ェ": 1022,
-      "##ハ": 1023,
-      "##υ": 1024,
-      "##र": 1025,
-      "##х": 1026,
-      "##も": 1027,
-      "##っ": 1028,
-      "##ょ": 1029,
-      "##に": 1030,
-      "##γ": 1031,
-      "##ც": 1032,
-      "##ე": 1033,
-      "##є": 1034,
-      "##м": 1035,
-      "##ܕ": 1036,
-      "##ܝ": 1037,
-      "##ܢ": 1038,
-      "##ܬ": 1039,
-      "##ณ": 1040,
-      "##ม": 1041,
-      "##ฮ": 1042,
-      "##ж": 1043,
-      "##ם": 1044,
-      "##ء": 1045,
-      "##ʊ": 1046,
-      "##ई": 1047,
-      "##め": 1048,
-      "##მ": 1049,
-      "##ム": 1050,
-      "##チ": 1051,
-      "##ᵻ": 1052,
-      "##ˌ": 1053,
-      "##ו": 1054,
-      "##ף": 1055,
-      "##წ": 1056,
-      "##ფ": 1057,
-      "##ャ": 1058,
-      "##モ": 1059,
-      "##ɐ": 1060,
-      "##ᅦ": 1061,
-      "##ᅩ": 1062,
-      "##ᆨ": 1063,
-      "##ᅵ": 1064,
-      "##ᆸ": 1065,
-      "##ᅧ": 1066,
-      "##ᆼ": 1067,
-      "##ᄋ": 1068,
-      "##ᆫ": 1069,
-      "##わ": 1070,
-      "##ı": 1071,
-      "##ქ": 1072,
-      "##დ": 1073,
-      "##ि": 1074,
-      "##ჲ": 1075,
-      "##ר": 1076,
-      "##セ": 1077,
-      "##オ": 1078,
-      "##ゆ": 1079,
-      "##せ": 1080,
-      "##ك": 1081,
-      "##ʿ": 1082,
-      "##ש": 1083,
-      "##מ": 1084,
-      "##צ": 1085,
-      "##п": 1086,
-      "##г": 1087,
-      "##カ": 1088,
-      "##ܠ": 1089,
-      "##ܗ": 1090,
-      "##ܐ": 1091,
-      "##ナ": 1092,
-      "##ミ": 1093,
-      "##こ": 1094,
-      "##を": 1095,
-      "##ψ": 1096,
-      "##サ": 1097,
-      "##ォ": 1098,
-      "##π": 1099,
-      "##ト": 1100,
-      "##у": 1101,
-      "##ح": 1102,
-      "##σ": 1103,
-      "##เ": 1104,
-      "##ป": 1105,
-      "##ш": 1106,
-      "##ゥ": 1107,
-      "##ロ": 1108,
-      "##া": 1109,
-      "##হ": 1110,
-      "##ɜ": 1111,
-      "##ة": 1112,
-      "##ص": 1113,
-      "##ס": 1114,
-      "##ث": 1115,
-      "##ჳ": 1116,
-      "##נ": 1117,
-      "##ذ": 1118,
-      "##ग": 1119,
-      "##ɫ": 1120,
-      "##ц": 1121,
-      "##ь": 1122,
-      "##ю": 1123
-    }
-  }
-}

tokenizer/merges.txt

@@ -1,647 +0,0 @@
-#version: 0.2
-Ġ t
-Ġt h
-Ġ a
-Ġth e</w>
-i n
-Ġ o
-Ġ ,</w>
-Ġ s
-e d</w>
-Ġ w
-e r
-Ġ .</w>
-Ġ i
-r e
-Ġ c
-n d</w>
-Ġ f
-Ġ b
-a t
-Ġo f</w>
-e r</w>
-e n
-a r
-o r
-i t
-Ġ p
-Ġ h
-Ġa nd</w>
-o n
-in g</w>
-a n
-r o
-Ġ m
-Ġ d
-e s</w>
-Ġi n</w>
-o n</w>
-Ġt o</w>
-o u
-i s
-Ġ a</w>
-i c
-Ġ T
-a l
-Ġ l
-Ġ =</w>
-Ġ re
-Ġ "</w>
-e s
-Ġ S
-a s</w>
-a l</w>
-i l
-e l
-i on</w>
-Ġ A
-Ġ C
-Ġ 1
-Ġ Ċ</w>
-u r
-ĠT h
-Ġ n
-a s
-Ġ @
-e c
-o m
-a c
-Ġ e
-Ġw as</w>
-Ġ M
-o r</w>
-a n</w>
-a m
-e n</w>
-o l
-Ġ in
-Ġ g
-Ġ '</w>
-Ġ B
-l y</w>
-a t</w>
-i v
-t s</w>
-ĠTh e</w>
-u s
-- @</w>
-Ġ@ -@</w>
-i s</w>
-Ġ I
-Ġw h
-i g
-Ġ H
-Ġs t
-o s
-u n
-t h
-Ġ P
-Ġw it
-Ġth at</w>
-i r
-Ġa s</w>
-e m
-Ġo n</w>
-r a
-Ġf or</w>
-Ġ R
-e t
-o w
-Ġ 2
-i d
-Ġ D
-l e</w>
-Ġwit h</w>
-l a
-en t</w>
-i m
-Ġ F
-e a
-i on
-Ġb y</w>
-Ġ )</w>
-Ġ (</w>
-Ġa l
-Ġc on
-en t
-Ġ W
-Ġi s</w>
-er e</w>
-Ġ G
-Ġ N
-Ġ L
-Ġh a
-er s</w>
-r i
-t h</w>
-t ed</w>
-u c
-Ġ J
-Ġ1 9
-e v
-u l
-Ġ v
-c e</w>
-at ion</w>
-ro m</w>
-Ġb e
-Ġ E
-i n</w>
-Ġth e
-Ġf rom</w>
-Ġ O
-t er</w>
-Ġp ro
-Ġa r
-a d
-Ġc om
-i c</w>
-a g
-Ġh is</w>
-Ġs h
-Ġa t</w>
-o v
-i es</w>
-o o
-p p
-s t
-c h
-Ġ r
-Ġ2 0
-a y</w>
-i f
-Ġw ere</w>
-Ġc h
-u t</w>
-s t</w>
-u t
-d s</w>
-o p
-u m
-Ġi t</w>
-o c
-t er
-l e
-ig h
-u d
-Ġe x
-ion s</w>
-at e</w>
-it y</w>
-at ed</w>
-Ġ un
-e p
-q u
-Ġn o
-Ġ K
-iv e</w>
-is t
-Ġo n
-am e</w>
-ou n
-i r</w>
-a b
-Ġ â
-in g
-Ġh e</w>
-l d</w>
-u g
-ic h</w>
-Ġa n</w>
-e d
-Ġ k
-Ġâ Ģ
-Ġha d</w>
-v e</w>
-a in
-Ġs e
-t ion</w>
-or e</w>
-re s
-Ġwh ich</w>
-ĠI n</w>
-o d
-th er</w>
-a k
-Ġs p
-a r</w>
-Ġ y
-ĠC h
-on g</w>
-Ġa c
-es t</w>
-Ġ U
-a p
-f f
-al ly</w>
-r it
-ĠS t
-u b
-g e</w>
-b er</w>
-e t</w>
-Ġb e</w>
-e ar
-Ġre c
-er s
-Ġf ir
-o t
-Ġar e</w>
-Ġa n
-c h</w>
-o g
-i a</w>
-es t
-in e</w>
-il l
-an d
-e l</w>
-ar y</w>
-e w</w>
-i d</w>
-Ġf or
-Ġ ;</w>
-Ġcom p
-Ġ V
-Ġin c
-t r
-Ġ20 0
-Ġthe ir</w>
-u s</w>
-Ġb ut</w>
-r an
-ic al</w>
-Ġfir st</w>
-Ġd e
-Ġin t
-Ġ ro
-s o</w>
-ĠâĢ ĵ</w>
-Ġno t</w>
-d ing</w>
-f ter</w>
-ur e</w>
-Ġp ar
-Ġ :</w>
-i an</w>
-Ġt w
-ou ld</w>
-Ġal so</w>
-Ġi ts</w>
-Ġw or
-u m</w>
-Ġo r</w>
-os t</w>
-0 0</w>
-ou r
-ar d</w>
-Ġre s
-m p
-u e</w>
-Ġa b
-is h</w>
-Ġcon t
-Ġa d
-ow n</w>
-al l</w>
-ou g
-Ġh er</w>
-as t</w>
-Ġ en
-om e</w>
-al l
-d ed</w>
-o w</w>
-Ġha ve</w>
-Ġ us
-ea r</w>
-ac k</w>
-d uc
-i al</w>
-s s
-en ts</w>
-a in</w>
-t ing</w>
-Ġon e</w>
-es s
-Ġh as</w>
-igh t</w>
-a v
-Ġe v
-ou t</w>
-a y
-en ce</w>
-Ġbe en</w>
-e w
-Ġtw o</w>
-Ġc l
-d er</w>
-im e</w>
-k s</w>
-es s</w>
-is h
-. @</w>
-Ġ@ .@</w>
-Ġp la
-Ġp l
-Ġo r
-u p</w>
-m ent</w>
-ur ing</w>
-ol l
-ĠI n
-Ġth is</w>
-Ġb ec
-Ġcom m
-Ġd is
-at er</w>
-ag e</w>
-Ġa pp
-ou s</w>
-e y</w>
-i l</w>
-p er
-ĠA l
-ion al</w>
-l ud
-el y</w>
-t t
-il e</w>
-i z
-Ġ j
-Ġwh o</w>
-Ġa g
-i b
-Ġthe y</w>
-f or
-Ġo v
-at h
-e g
-Ġs c
-i p
-Ġ20 1
-Ġ 3
-Ġp er
-or y</w>
-Ġd es
-id e</w>
-Ġs er
-s e</w>
-ĠH e</w>
-la nd</w>
-at ions</w>
-r ic
-i t</w>
-re s</w>
-er ed</w>
-Ġp re
-ĠS h
-an ce</w>
-or t</w>
-an t</w>
-, @</w>
-Ġ@ ,@</w>
-el l</w>
-Ġ Y
-n ed</w>
-el l
-it e</w>
-Ġinc lud
-Ġre p
-Ġa fter</w>
-Ġs uc
-re e</w>
-an y</w>
-i m</w>
-or t
-Ġ1 8
-Ġs u
-ad e</w>
-ou r</w>
-ĠU n
-ĠI t</w>
-i k
-ĠM ar
-em ber</w>
-Ġ 1</w>
-e en</w>
-a nd</w>
-Ġs ec
-ic e</w>
-Ġt ime</w>
-ĠA n
-Ġint o</w>
-Ġf in
-Ġo ther</w>
-Ġa tt
-il l</w>
-re n
-ac h
-as s
-er al</w>
-es e</w>
-s h
-al s</w>
-it ion</w>
-oug h</w>
-l es</w>
-am p
-Ġw ould</w>
-Ġm ore</w>
-ro ug
-ri b
-er y</w>
-ac e</w>
-Ġ A</w>
-Ġpla y
-it ed</w>
-k ed</w>
-is t</w>
-i ed</w>
-Ġ 2</w>
-as ed</w>
-ing s</w>
-an g
-a m</w>
-i p</w>
-Ġb o
-ab le</w>
-t y</w>
-Ġch ar
-Ġc ent
-et w
-at es</w>
-ro p
-Ġ I</w>
-u nd</w>
-ĠA m
-c es</w>
-o in
-Ġin ter
-u p
-c t
-on e</w>
-Ġt ra
-an t
-ec t
-Ġal l</w>
-e f
-Ġcon s
-ub l
-n ing</w>
-an s</w>
-Ġf e
-us t</w>
-Ġ 0
-Ġre m
-as e</w>
-on g
-Ġwh en</w>
-e b
-ĠW h
-Ġe ar
-ev er</w>
-Ġov er</w>
-Ġk n
-a us
-Ġp os
-a d</w>
-er m
-Ġsh e</w>
-Ġ ra
-Ġd uring</w>
-as on</w>
-v i
-Ġex p
-Ġl ea
-Ġ el
-Ġ 4
-Ġon ly</w>
-o nd</w>
-Ġd ec
-Ġac c
-Ġo ff
-is s
-Ġf l
-ĠE n
-o t</w>
-en s
-os e</w>
-ak e</w>
-o m</w>
-Ġs ev
-ac h</w>
-etw een</w>
-er n
-Ġ 3</w>
-Ġp r
-Ġg ro
-r uc
-Ġd i
-Ġ19 9
-ĠA r
-Ġg ame</w>
-Ġh im</w>
-oo k</w>
-Ġ up</w>
-Ġab out</w>
-Ġre l
-for m
-Ġth ree</w>
-at t
-ĠC om
-Ġs a
-ear s</w>
-Ġ 5
-r y</w>
-Ġi mp
-Ġm ost</w>
-f er
-Ġp res
-Ġf il
-Ġb etween</w>
-Ġbe g
-p h
-or s</w>
-Ġth an</w>
-Ġrec or
-o b
-er ic
-at ing</w>
-Ġth roug
-k ing</w>
-Ġo ut</w>
-Ġn um
-oo d</w>
-oll ow
-ac t
-u il
-Ġc re
-ol og
-at ional</w>
-Ġpro duc
-Ġwh ile</w>
-Ġl ater</w>
-Ġw rit
-e x
-Ġst ar
-Ġsp ec
-e e
-ish ed</w>
-Ġre g
-is ion</w>
-ou th</w>
-Ġre le
-Ġa ss
-Ġse ason</w>
-Ġm ade</w>
-il y</w>
-r u
-o y
-t ur
-t e</w>
-Ġ qu
-Ġm ov
-ur y</w>
-ĠAm eric
-em ent</w>
-c c
-ou nd</w>
-Ġl ar
-Ġfor m
-ec t</w>
-Ġde f
-Ġm us
-ĠP ar
-Ġm e
-Ġs ub
-w ay</w>
-o p</w>
-o h
-el d</w>
-i e</w>
-em p
-am es</w>
-er n</w>
-Ġn or
-iv ed</w>
-ev el
-Ġsuc h</w>
-ar ds</w>
-Ġin d
-ik e</w>
-Ġg en
-er t
-Ġy ear</w>
-Ġus ed</w>
-Ġn ew</w>
-Ġ 5</w>
-Ġal b
-s p
-y p
-Ġwit h
-Ġwh ere</w>
-ic s</w>
-ĠTh is</w>
-Ġthe m</w>
-w n</w>

tokenizer/special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer/tokenizer_config.json

@@ -1,33 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer/vocab.json

@@ -1,1002 +0,0 @@
-{
-  "!": 2,
-  "!</w>": 345,
-  "\"": 3,
-  "\"</w>": 344,
-  "#": 4,
-  "#</w>": 325,
-  "$": 5,
-  "$</w>": 348,
-  "%": 6,
-  "%</w>": 351,
-  "&": 7,
-  "&</w>": 352,
-  "'": 8,
-  "'</w>": 296,
-  "(": 9,
-  "(</w>": 318,
-  ")": 10,
-  ")</w>": 330,
-  "*": 11,
-  "*</w>": 327,
-  "+": 12,
-  "+</w>": 341,
-  ",": 13,
-  ",</w>": 279,
-  ",@</w>": 754,
-  "-": 14,
-  "-</w>": 276,
-  "-@</w>": 439,
-  ".": 15,
-  ".</w>": 253,
-  ".@</w>": 695,
-  "/": 16,
-  "/</w>": 350,
-  "0": 17,
-  "00</w>": 647,
-  "0</w>": 216,
-  "1": 18,
-  "1</w>": 222,
-  "2": 19,
-  "2</w>": 231,
-  "3": 20,
-  "3</w>": 243,
-  "4": 21,
-  "4</w>": 233,
-  "5": 22,
-  "5</w>": 240,
-  "6": 23,
-  "6</w>": 226,
-  "7": 24,
-  "7</w>": 215,
-  "8": 25,
-  "8</w>": 236,
-  "9": 26,
-  "9</w>": 242,
-  ":": 27,
-  ":</w>": 353,
-  ";": 28,
-  ";</w>": 317,
-  "<": 29,
-  "<</w>": 340,
-  "<|endoftext|>": 1,
-  "<|startoftext|>": 0,
-  "=": 30,
-  "=</w>": 342,
-  ">": 31,
-  "></w>": 300,
-  "?": 32,
-  "?</w>": 346,
-  "@": 33,
-  "@</w>": 320,
-  "A": 34,
-  "A</w>": 227,
-  "B": 35,
-  "B</w>": 258,
-  "C": 36,
-  "C</w>": 239,
-  "D": 37,
-  "D</w>": 255,
-  "E": 38,
-  "E</w>": 246,
-  "F": 39,
-  "F</w>": 213,
-  "G": 40,
-  "G</w>": 283,
-  "H": 41,
-  "H</w>": 219,
-  "I": 42,
-  "I</w>": 237,
-  "J": 43,
-  "J</w>": 251,
-  "K": 44,
-  "K</w>": 254,
-  "L": 45,
-  "L</w>": 218,
-  "M": 46,
-  "M</w>": 234,
-  "N": 47,
-  "N</w>": 238,
-  "O": 48,
-  "O</w>": 265,
-  "P": 49,
-  "P</w>": 245,
-  "Q": 50,
-  "Q</w>": 309,
-  "R": 51,
-  "R</w>": 264,
-  "S": 52,
-  "S</w>": 230,
-  "T": 53,
-  "T</w>": 235,
-  "U": 54,
-  "U</w>": 268,
-  "V": 55,
-  "V</w>": 248,
-  "W": 56,
-  "W</w>": 274,
-  "X": 57,
-  "X</w>": 263,
-  "Y": 58,
-  "Y</w>": 310,
-  "Z": 59,
-  "Z</w>": 207,
-  "[": 60,
-  "[</w>": 270,
-  "\\": 61,
-  "\\</w>": 338,
-  "]": 62,
-  "]</w>": 289,
-  "^": 63,
-  "^</w>": 331,
-  "_": 64,
-  "_</w>": 334,
-  "`": 65,
-  "`</w>": 347,
-  "a": 66,
-  "a</w>": 197,
-  "ab": 555,
-  "able</w>": 820,
-  "ac": 420,
-  "ace</w>": 806,
-  "ach": 791,
-  "ach</w>": 885,
-  "ack</w>": 670,
-  "act": 929,
-  "ad": 508,
-  "ad</w>": 860,
-  "ade</w>": 771,
-  "ag": 511,
-  "age</w>": 710,
-  "ain": 568,
-  "ain</w>": 675,
-  "ak": 577,
-  "ake</w>": 882,
-  "al": 397,
-  "al</w>": 405,
-  "all": 664,
-  "all</w>": 658,
-  "ally</w>": 588,
-  "als</w>": 796,
-  "am": 426,
-  "am</w>": 817,
-  "ame</w>": 552,
-  "ames</w>": 976,
-  "amp": 800,
-  "an": 384,
-  "an</w>": 425,
-  "ance</w>": 751,
-  "and": 609,
-  "and</w>": 780,
-  "ang": 816,
-  "ans</w>": 844,
-  "ant": 837,
-  "ant</w>": 753,
-  "any</w>": 766,
-  "ap": 586,
-  "ar": 376,
-  "ar</w>": 579,
-  "ard</w>": 649,
-  "ards</w>": 982,
-  "ary</w>": 611,
-  "as": 416,
-  "as</w>": 404,
-  "ase</w>": 849,
-  "ased</w>": 814,
-  "ason</w>": 865,
-  "ass": 792,
-  "ast</w>": 661,
-  "at": 372,
-  "at</w>": 434,
-  "ate</w>": 541,
-  "ated</w>": 543,
-  "ater</w>": 709,
-  "ates</w>": 825,
-  "ath": 730,
-  "ating</w>": 922,
-  "ation</w>": 497,
-  "ational</w>": 933,
-  "ations</w>": 744,
-  "att": 903,
-  "aus": 858,
-  "av": 681,
-  "ay": 684,
-  "ay</w>": 523,
-  "b": 67,
-  "b</w>": 212,
-  "ber</w>": 593,
-  "c": 68,
-  "c</w>": 224,
-  "cc": 960,
-  "ce</w>": 496,
-  "ces</w>": 830,
-  "ch": 520,
-  "ch</w>": 603,
-  "ct": 834,
-  "d": 69,
-  "d</w>": 196,
-  "ded</w>": 665,
-  "der</w>": 690,
-  "ding</w>": 633,
-  "ds</w>": 530,
-  "duc": 671,
-  "e": 70,
-  "e</w>": 195,
-  "ea": 471,
-  "ear": 596,
-  "ear</w>": 669,
-  "ears</w>": 906,
-  "eb": 852,
-  "ec": 418,
-  "ect": 838,
-  "ect</w>": 964,
-  "ed": 563,
-  "ed</w>": 362,
-  "ee": 941,
-  "een</w>": 779,
-  "ef": 840,
-  "eg": 731,
-  "el": 407,
-  "el</w>": 610,
-  "eld</w>": 973,
-  "ell": 759,
-  "ell</w>": 756,
-  "ely</w>": 719,
-  "em": 455,
-  "ember</w>": 777,
-  "ement</w>": 959,
-  "emp": 975,
-  "en": 375,
-  "en</w>": 427,
-  "ence</w>": 685,
-  "ens": 880,
-  "ent": 478,
-  "ent</w>": 468,
-  "ents</w>": 674,
-  "ep": 545,
-  "er": 364,
-  "er</w>": 374,
-  "eral</w>": 793,
-  "ere</w>": 481,
-  "ered</w>": 748,
-  "eric": 921,
-  "erm": 861,
-  "ern": 887,
-  "ern</w>": 977,
-  "ers": 598,
-  "ers</w>": 486,
-  "ert": 986,
-  "ery</w>": 805,
-  "es": 402,
-  "es</w>": 388,
-  "ese</w>": 794,
-  "ess": 678,
-  "ess</w>": 693,
-  "est": 606,
-  "est</w>": 584,
-  "et": 460,
-  "et</w>": 594,
-  "etw": 824,
-  "etween</w>": 886,
-  "ev": 493,
-  "evel": 980,
-  "ever</w>": 855,
-  "ew": 687,
-  "ew</w>": 612,
-  "ex": 938,
-  "ey</w>": 713,
-  "f": 71,
-  "f</w>": 209,
-  "fer": 911,
-  "ff": 587,
-  "for": 728,
-  "form": 901,
-  "fter</w>": 634,
-  "g": 72,
-  "g</w>": 214,
-  "ge</w>": 592,
-  "h": 73,
-  "h</w>": 203,
-  "i": 74,
-  "i</w>": 205,
-  "ia</w>": 605,
-  "ial</w>": 672,
-  "ian</w>": 638,
-  "ib": 726,
-  "ic": 395,
-  "ic</w>": 510,
-  "ical</w>": 625,
-  "ice</w>": 782,
-  "ich</w>": 561,
-  "ics</w>": 996,
-  "id": 463,
-  "id</w>": 613,
-  "ide</w>": 739,
-  "ie</w>": 974,
-  "ied</w>": 812,
-  "ies</w>": 516,
-  "if": 524,
-  "ig": 444,
-  "igh": 537,
-  "ight</w>": 680,
-  "ik": 775,
-  "ike</w>": 984,
-  "il": 406,
-  "il</w>": 714,
-  "ile</w>": 721,
-  "ill": 608,
-  "ill</w>": 789,
-  "ily</w>": 950,
-  "im": 469,
-  "im</w>": 767,
-  "ime</w>": 691,
-  "in": 358,
-  "in</w>": 501,
-  "ine</w>": 607,
-  "ing": 557,
-  "ing</w>": 383,
-  "ings</w>": 815,
-  "ion": 472,
-  "ion</w>": 408,
-  "ional</w>": 717,
-  "ions</w>": 540,
-  "ip": 733,
-  "ip</w>": 818,
-  "ir": 453,
-  "ir</w>": 554,
-  "is": 393,
-  "is</w>": 441,
-  "ish": 694,
-  "ish</w>": 654,
-  "ished</w>": 942,
-  "ision</w>": 944,
-  "iss": 876,
-  "ist": 550,
-  "ist</w>": 811,
-  "it": 378,
-  "it</w>": 746,
-  "ite</w>": 760,
-  "ited</w>": 809,
-  "ition</w>": 797,
-  "ity</w>": 542,
-  "iv": 435,
-  "ive</w>": 549,
-  "ived</w>": 979,
-  "iz": 722,
-  "j": 75,
-  "j</w>": 288,
-  "k": 76,
-  "k</w>": 210,
-  "ked</w>": 810,
-  "king</w>": 924,
-  "ks</w>": 692,
-  "l": 77,
-  "l</w>": 201,
-  "la": 467,
-  "land</w>": 743,
-  "ld</w>": 559,
-  "le": 536,
-  "le</w>": 465,
-  "les</w>": 799,
-  "lud": 718,
-  "ly</w>": 433,
-  "m": 78,
-  "m</w>": 202,
-  "ment</w>": 701,
-  "mp": 651,
-  "n": 79,
-  "n</w>": 199,
-  "nd</w>": 369,
-  "ned</w>": 758,
-  "ning</w>": 843,
-  "o": 80,
-  "o</w>": 198,
-  "ob": 920,
-  "oc": 534,
-  "od": 575,
-  "og": 604,
-  "oh": 972,
-  "oin": 831,
-  "ol": 428,
-  "oll": 703,
-  "ollow": 928,
-  "olog": 932,
-  "om": 419,
-  "om</w>": 883,
-  "ome</w>": 663,
-  "on": 382,
-  "on</w>": 390,
-  "ond</w>": 872,
-  "one</w>": 835,
-  "ong": 850,
-  "ong</w>": 582,
-  "oo": 517,
-  "ood</w>": 927,
-  "ook</w>": 897,
-  "op": 531,
-  "op</w>": 971,
-  "or": 377,
-  "or</w>": 424,
-  "ore</w>": 571,
-  "ors</w>": 917,
-  "ort": 768,
-  "ort</w>": 752,
-  "ory</w>": 737,
-  "os": 447,
-  "ose</w>": 881,
-  "ost</w>": 646,
-  "ot": 600,
-  "ot</w>": 879,
-  "ou": 392,
-  "oug": 659,
-  "ough</w>": 798,
-  "ould</w>": 640,
-  "oun": 553,
-  "ound</w>": 961,
-  "our": 648,
-  "our</w>": 772,
-  "ous</w>": 712,
-  "out</w>": 683,
-  "outh</w>": 945,
-  "ov": 515,
-  "ow": 461,
-  "ow</w>": 666,
-  "own</w>": 657,
-  "oy": 952,
-  "p": 81,
-  "p</w>": 217,
-  "per": 715,
-  "ph": 916,
-  "pp": 518,
-  "q": 82,
-  "q</w>": 280,
-  "qu": 546,
-  "r": 83,
-  "r</w>": 204,
-  "ra": 457,
-  "ran": 624,
-  "re": 367,
-  "ree</w>": 765,
-  "ren": 790,
-  "res": 572,
-  "res</w>": 747,
-  "ri": 487,
-  "rib": 804,
-  "ric": 745,
-  "rit": 589,
-  "ro": 385,
-  "rom</w>": 498,
-  "rop": 826,
-  "roug": 803,
-  "ru": 951,
-  "ruc": 891,
-  "ry</w>": 908,
-  "s": 84,
-  "s</w>": 206,
-  "se</w>": 741,
-  "sh": 795,
-  "so</w>": 630,
-  "sp": 992,
-  "ss": 673,
-  "st": 519,
-  "st</w>": 528,
-  "t": 85,
-  "t</w>": 208,
-  "te</w>": 954,
-  "ted</w>": 489,
-  "ter": 535,
-  "ter</w>": 505,
-  "th": 449,
-  "th</w>": 488,
-  "ther</w>": 576,
-  "ting</w>": 676,
-  "tion</w>": 570,
-  "tr": 619,
-  "ts</w>": 436,
-  "tt": 720,
-  "tur": 953,
-  "ty</w>": 821,
-  "u": 86,
-  "u</w>": 229,
-  "ub": 591,
-  "ubl": 842,
-  "uc": 490,
-  "ud": 538,
-  "ue</w>": 652,
-  "ug": 560,
-  "uil": 930,
-  "ul": 494,
-  "um": 532,
-  "um</w>": 644,
-  "un": 448,
-  "und</w>": 828,
-  "up": 833,
-  "up</w>": 700,
-  "ur": 413,
-  "ure</w>": 635,
-  "uring</w>": 702,
-  "ury</w>": 957,
-  "us": 438,
-  "us</w>": 622,
-  "ust</w>": 846,
-  "ut": 529,
-  "ut</w>": 527,
-  "v": 87,
-  "v</w>": 232,
-  "ve</w>": 567,
-  "vi": 866,
-  "w": 88,
-  "w</w>": 250,
-  "way</w>": 970,
-  "wn</w>": 999,
-  "x": 89,
-  "x</w>": 269,
-  "y": 90,
-  "y</w>": 211,
-  "yp": 993,
-  "z": 91,
-  "z</w>": 228,
-  "|": 92,
-  "|</w>": 304,
-  "}": 93,
-  "}</w>": 336,
-  "~": 94,
-  "~</w>": 343,
-  "¡": 95,
-  "¡</w>": 220,
-  "¢": 96,
-  "¢</w>": 306,
-  "£": 97,
-  "£</w>": 323,
-  "¤": 98,
-  "¤</w>": 292,
-  "¥": 99,
-  "¥</w>": 339,
-  "¦": 100,
-  "¦</w>": 303,
-  "§": 101,
-  "§</w>": 275,
-  "¨": 102,
-  "¨</w>": 282,
-  "©": 103,
-  "©</w>": 259,
-  "ª": 104,
-  "ª</w>": 286,
-  "«": 105,
-  "«</w>": 266,
-  "¬": 106,
-  "¬</w>": 319,
-  "®": 107,
-  "®</w>": 329,
-  "¯": 108,
-  "¯</w>": 287,
-  "°": 109,
-  "°</w>": 298,
-  "±": 110,
-  "±</w>": 200,
-  "²": 111,
-  "²</w>": 284,
-  "³": 112,
-  "³</w>": 272,
-  "´": 113,
-  "´</w>": 307,
-  "µ": 114,
-  "µ</w>": 261,
-  "¶": 115,
-  "¶</w>": 301,
-  "·": 116,
-  "·</w>": 326,
-  "¸": 117,
-  "¸</w>": 257,
-  "¹": 118,
-  "¹</w>": 241,
-  "º": 119,
-  "º</w>": 260,
-  "»": 120,
-  "»</w>": 247,
-  "¼": 121,
-  "¼</w>": 305,
-  "½": 122,
-  "½</w>": 294,
-  "¾": 123,
-  "¾</w>": 316,
-  "¿": 124,
-  "¿</w>": 271,
-  "Â": 125,
-  "Ã": 126,
-  "Ä": 127,
-  "Å": 128,
-  "Æ": 129,
-  "Ç": 130,
-  "È": 131,
-  "É": 132,
-  "Ê": 133,
-  "Ë": 134,
-  "Ì": 135,
-  "Í": 136,
-  "Î": 137,
-  "Ï": 138,
-  "Ð": 139,
-  "Ñ": 140,
-  "Ö": 141,
-  "×": 142,
-  "Ø": 143,
-  "Ù": 144,
-  "Ü": 145,
-  "à": 146,
-  "á": 147,
-  "â": 148,
-  "ã": 149,
-  "ä": 150,
-  "å": 151,
-  "æ": 152,
-  "ç": 153,
-  "è": 154,
-  "é": 155,
-  "ë": 156,
-  "ì": 157,
-  "ï": 158,
-  "Ċ": 159,
-  "Ċ</w>": 349,
-  "Ġ": 160,
-  "Ġ\"</w>": 401,
-  "Ġ'</w>": 431,
-  "Ġ(</w>": 475,
-  "Ġ)</w>": 474,
-  "Ġ,</w>": 360,
-  "Ġ.</w>": 365,
-  "Ġ0": 847,
-  "Ġ1": 411,
-  "Ġ18": 769,
-  "Ġ19": 492,
-  "Ġ199": 893,
-  "Ġ1</w>": 778,
-  "Ġ2": 462,
-  "Ġ20": 522,
-  "Ġ200": 620,
-  "Ġ201": 734,
-  "Ġ2</w>": 813,
-  "Ġ3": 735,
-  "Ġ3</w>": 888,
-  "Ġ4": 870,
-  "Ġ5": 907,
-  "Ġ5</w>": 990,
-  "Ġ:</w>": 637,
-  "Ġ;</w>": 615,
-  "Ġ</w>": 333,
-  "Ġ=</w>": 399,
-  "Ġ@": 417,
-  "Ġ@,@</w>": 755,
-  "Ġ@-@</w>": 440,
-  "Ġ@.@</w>": 696,
-  "ĠA": 409,
-  "ĠA</w>": 807,
-  "ĠAl": 716,
-  "ĠAm": 829,
-  "ĠAmeric": 958,
-  "ĠAn": 784,
-  "ĠAr": 894,
-  "ĠB": 432,
-  "ĠC": 410,
-  "ĠCh": 581,
-  "ĠCom": 904,
-  "ĠD": 464,
-  "ĠE": 500,
-  "ĠEn": 878,
-  "ĠF": 470,
-  "ĠG": 482,
-  "ĠH": 445,
-  "ĠHe</w>": 742,
-  "ĠI": 442,
-  "ĠI</w>": 827,
-  "ĠIn": 704,
-  "ĠIn</w>": 574,
-  "ĠIt</w>": 774,
-  "ĠJ": 491,
-  "ĠK": 548,
-  "ĠL": 484,
-  "ĠM": 423,
-  "ĠMar": 776,
-  "ĠN": 483,
-  "ĠO": 504,
-  "ĠP": 450,
-  "ĠPar": 967,
-  "ĠR": 459,
-  "ĠS": 403,
-  "ĠSh": 750,
-  "ĠSt": 590,
-  "ĠT": 396,
-  "ĠTh": 414,
-  "ĠThe</w>": 437,
-  "ĠThis</w>": 997,
-  "ĠU": 585,
-  "ĠUn": 773,
-  "ĠV": 617,
-  "ĠW": 479,
-  "ĠWh": 853,
-  "ĠY": 757,
-  "Ġa": 356,
-  "Ġa</w>": 394,
-  "Ġab": 653,
-  "Ġabout</w>": 899,
-  "Ġac": 583,
-  "Ġacc": 874,
-  "Ġad": 656,
-  "Ġafter</w>": 763,
-  "Ġag": 725,
-  "Ġal": 476,
-  "Ġalb": 991,
-  "Ġall</w>": 839,
-  "Ġalso</w>": 641,
-  "Ġan": 602,
-  "Ġan</w>": 562,
-  "Ġand</w>": 381,
-  "Ġapp": 711,
-  "Ġar": 507,
-  "Ġare</w>": 601,
-  "Ġas</w>": 454,
-  "Ġass": 947,
-  "Ġat</w>": 514,
-  "Ġatt": 788,
-  "Ġb": 371,
-  "Ġbe": 499,
-  "Ġbe</w>": 595,
-  "Ġbec": 706,
-  "Ġbeen</w>": 686,
-  "Ġbeg": 915,
-  "Ġbetween</w>": 914,
-  "Ġbo": 819,
-  "Ġbut</w>": 623,
-  "Ġby</w>": 473,
-  "Ġc": 368,
-  "Ġcent": 823,
-  "Ġch": 526,
-  "Ġchar": 822,
-  "Ġcl": 689,
-  "Ġcom": 509,
-  "Ġcomm": 707,
-  "Ġcomp": 616,
-  "Ġcon": 477,
-  "Ġcons": 841,
-  "Ġcont": 655,
-  "Ġcre": 931,
-  "Ġd": 387,
-  "Ġde": 627,
-  "Ġdec": 873,
-  "Ġdef": 965,
-  "Ġdes": 738,
-  "Ġdi": 892,
-  "Ġdis": 708,
-  "Ġduring</w>": 864,
-  "Ġe": 421,
-  "Ġear": 854,
-  "Ġel": 869,
-  "Ġen": 662,
-  "Ġev": 682,
-  "Ġex": 539,
-  "Ġexp": 867,
-  "Ġf": 370,
-  "Ġfe": 845,
-  "Ġfil": 913,
-  "Ġfin": 786,
-  "Ġfir": 599,
-  "Ġfirst</w>": 626,
-  "Ġfl": 877,
-  "Ġfor": 614,
-  "Ġfor</w>": 458,
-  "Ġform": 963,
-  "Ġfrom</w>": 503,
-  "Ġg": 430,
-  "Ġgame</w>": 895,
-  "Ġgen": 985,
-  "Ġgro": 890,
-  "Ġh": 380,
-  "Ġha": 485,
-  "Ġhad</w>": 566,
-  "Ġhas</w>": 679,
-  "Ġhave</w>": 667,
-  "Ġhe</w>": 558,
-  "Ġher</w>": 660,
-  "Ġhim</w>": 896,
-  "Ġhis</w>": 512,
-  "Ġi": 366,
-  "Ġimp": 909,
-  "Ġin": 429,
-  "Ġin</w>": 389,
-  "Ġinc": 618,
-  "Ġinclud": 761,
-  "Ġind": 983,
-  "Ġint": 628,
-  "Ġinter": 832,
-  "Ġinto</w>": 785,
-  "Ġis</w>": 480,
-  "Ġit</w>": 533,
-  "Ġits</w>": 642,
-  "Ġj": 723,
-  "Ġk": 564,
-  "Ġkn": 857,
-  "Ġl": 398,
-  "Ġlar": 962,
-  "Ġlater</w>": 936,
-  "Ġlea": 868,
-  "Ġm": 386,
-  "Ġmade</w>": 949,
-  "Ġme": 968,
-  "Ġmore</w>": 802,
-  "Ġmost</w>": 910,
-  "Ġmov": 956,
-  "Ġmus": 966,
-  "Ġn": 415,
-  "Ġnew</w>": 989,
-  "Ġno": 547,
-  "Ġnor": 978,
-  "Ġnot</w>": 632,
-  "Ġnum": 926,
-  "Ġo": 359,
-  "Ġof</w>": 373,
-  "Ġoff": 875,
-  "Ġon": 551,
-  "Ġon</w>": 456,
-  "Ġone</w>": 677,
-  "Ġonly</w>": 871,
-  "Ġor": 699,
-  "Ġor</w>": 645,
-  "Ġother</w>": 787,
-  "Ġout</w>": 925,
-  "Ġov": 729,
-  "Ġover</w>": 856,
-  "Ġp": 379,
-  "Ġpar": 636,
-  "Ġper": 736,
-  "Ġpl": 698,
-  "Ġpla": 697,
-  "Ġplay": 808,
-  "Ġpos": 859,
-  "Ġpr": 889,
-  "Ġpre": 749,
-  "Ġpres": 912,
-  "Ġpro": 506,
-  "Ġproduc": 934,
-  "Ġqu": 955,
-  "Ġr": 521,
-  "Ġra": 863,
-  "Ġre": 400,
-  "Ġrec": 597,
-  "Ġrecor": 919,
-  "Ġreg": 943,
-  "Ġrel": 900,
-  "Ġrele": 946,
-  "Ġrem": 848,
-  "Ġrep": 762,
-  "Ġres": 650,
-  "Ġro": 629,
-  "Ġs": 361,
-  "Ġsa": 905,
-  "Ġsc": 732,
-  "Ġse": 569,
-  "Ġseason</w>": 948,
-  "Ġsec": 781,
-  "Ġser": 740,
-  "Ġsev": 884,
-  "Ġsh": 513,
-  "Ġshe</w>": 862,
-  "Ġsp": 578,
-  "Ġspec": 940,
-  "Ġst": 446,
-  "Ġstar": 939,
-  "Ġsu": 770,
-  "Ġsub": 969,
-  "Ġsuc": 764,
-  "Ġsuch</w>": 981,
-  "Ġt": 354,
-  "Ġth": 355,
-  "Ġthan</w>": 918,
-  "Ġthat</w>": 452,
-  "Ġthe": 502,
-  "Ġthe</w>": 357,
-  "Ġtheir</w>": 621,
-  "Ġthem</w>": 998,
-  "Ġthey</w>": 727,
-  "Ġthis</w>": 705,
-  "Ġthree</w>": 902,
-  "Ġthroug": 923,
-  "Ġtime</w>": 783,
-  "Ġto</w>": 391,
-  "Ġtra": 836,
-  "Ġtw": 639,
-  "Ġtwo</w>": 688,
-  "Ġun": 544,
-  "Ġup</w>": 898,
-  "Ġus": 668,
-  "Ġused</w>": 988,
-  "Ġv": 495,
-  "Ġw": 363,
-  "Ġwas</w>": 422,
-  "Ġwere</w>": 525,
-  "Ġwh": 443,
-  "Ġwhen</w>": 851,
-  "Ġwhere</w>": 995,
-  "Ġwhich</w>": 573,
-  "Ġwhile</w>": 935,
-  "Ġwho</w>": 724,
-  "Ġwit": 451,
-  "Ġwith": 994,
-  "Ġwith</w>": 466,
-  "Ġwor": 643,
-  "Ġwould</w>": 801,
-  "Ġwrit": 937,
-  "Ġy": 580,
-  "Ġyear</w>": 987,
-  "Ġâ": 556,
-  "ĠâĢ": 565,
-  "ĠâĢĵ</w>": 631,
-  "ĠĊ</w>": 412,
-  "Ģ": 161,
-  "Ģ</w>": 223,
-  "ģ": 162,
-  "ģ</w>": 273,
-  "Ĥ": 163,
-  "Ĥ</w>": 262,
-  "ĥ": 164,
-  "ĥ</w>": 337,
-  "Ħ": 165,
-  "Ħ</w>": 278,
-  "ħ": 166,
-  "ħ</w>": 281,
-  "Ĩ": 167,
-  "Ĩ</w>": 308,
-  "ĩ": 168,
-  "ĩ</w>": 225,
-  "Ī": 169,
-  "Ī</w>": 221,
-  "ī": 170,
-  "ī</w>": 244,
-  "Ĭ": 171,
-  "Ĭ</w>": 315,
-  "ĭ": 172,
-  "ĭ</w>": 321,
-  "Į": 173,
-  "Į</w>": 324,
-  "į": 174,
-  "į</w>": 302,
-  "İ": 175,
-  "İ</w>": 249,
-  "ı": 176,
-  "ı</w>": 332,
-  "IJ": 177,
-  "IJ</w>": 295,
-  "ij": 178,
-  "ij</w>": 313,
-  "Ĵ": 179,
-  "Ĵ</w>": 328,
-  "ĵ": 180,
-  "ĵ</w>": 312,
-  "Ķ": 181,
-  "Ķ</w>": 256,
-  "ķ": 182,
-  "ķ</w>": 314,
-  "ĸ": 183,
-  "ĸ</w>": 277,
-  "Ĺ": 184,
-  "Ĺ</w>": 322,
-  "ĺ": 185,
-  "ĺ</w>": 285,
-  "Ļ": 186,
-  "Ļ</w>": 267,
-  "ļ": 187,
-  "ļ</w>": 290,
-  "Ľ": 188,
-  "Ľ</w>": 311,
-  "ľ": 189,
-  "ľ</w>": 299,
-  "Ŀ": 190,
-  "Ŀ</w>": 291,
-  "ŀ": 191,
-  "ŀ</w>": 293,
-  "Ł": 192,
-  "Ł</w>": 335,
-  "ł": 193,
-  "ł</w>": 252,
-  "Ń": 194,
-  "Ń</w>": 297
-}

tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

unet/config.json

@@ -1,114 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_commit_hash": null,
-  "_diffusers_version": "0.19.3",
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-torch/snapshots/a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d/unet",
-  "_use_default_values": [
-    "time_cond_proj_dim",
-    "time_embedding_dim",
-    "addition_embed_type",
-    "class_embed_type",
-    "addition_time_embed_dim",
-    "resnet_skip_time_act",
-    "transformer_layers_per_block",
-    "num_class_embeds",
-    "conv_out_kernel",
-    "mid_block_type",
-    "time_embedding_type",
-    "class_embeddings_concat",
-    "time_embedding_act_fn",
-    "resnet_time_scale_shift",
-    "timestep_post_act",
-    "conv_in_kernel",
-    "upcast_attention",
-    "encoder_hid_dim_type",
-    "addition_embed_type_num_heads",
-    "dual_cross_attention",
-    "projection_class_embeddings_input_dim",
-    "mid_block_only_cross_attention",
-    "num_attention_heads",
-    "use_linear_projection",
-    "cross_attention_norm",
-    "only_cross_attention",
-    "encoder_hid_dim",
-    "resnet_out_scale_factor"
-  ],
-  "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
-  "block_out_channels": [
-    32,
-    64
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 32,
-  "cross_attention_norm": null,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 4,
-  "layers_per_block": 2,
-  "mid_block_only_cross_attention": null,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "model_type": "unet",
-  "neuron": {
-    "auto_cast": null,
-    "auto_cast_type": null,
-    "compiler_type": "neuronx-cc",
-    "compiler_version": "2.8.0.25+a3ad0f342",
-    "disable_fallback": false,
-    "disable_fast_relayout": false,
-    "dynamic_batch_size": false,
-    "input_names": [
-      "sample",
-      "timestep",
-      "encoder_hidden_states"
-    ],
-    "output_names": [
-      "sample"
-    ],
-    "static_batch_size": 1,
-    "static_height": 32,
-    "static_num_channels": 4,
-    "static_sequence_length": 77,
-    "static_width": 32
-  },
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
-  "resnet_time_scale_shift": "default",
-  "sample_size": 64,
-  "time_cond_proj_dim": null,
-  "time_embedding_act_fn": null,
-  "time_embedding_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "transformer_layers_per_block": 1,
-  "transformers_version": null,
-  "up_block_types": [
-    "CrossAttnUpBlock2D",
-    "UpBlock2D"
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": false
-}

unet/model.neuron

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d2a4eda9d58db0f5bb40ada69cb8e6bd4f5f052f59c30967b07c3bf13cd32b1
-size 8308508

vae_decoder/config.json

@@ -1,52 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_commit_hash": null,
-  "_diffusers_version": "0.19.3",
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-torch/snapshots/a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d/vae",
-  "_use_default_values": [
-    "force_upcast",
-    "scaling_factor"
-  ],
-  "act_fn": "silu",
-  "block_out_channels": [
-    32,
-    64
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "force_upcast": true,
-  "in_channels": 3,
-  "latent_channels": 4,
-  "layers_per_block": 1,
-  "model_type": "vae-decoder",
-  "neuron": {
-    "auto_cast": null,
-    "auto_cast_type": null,
-    "compiler_type": "neuronx-cc",
-    "compiler_version": "2.8.0.25+a3ad0f342",
-    "disable_fallback": false,
-    "disable_fast_relayout": false,
-    "dynamic_batch_size": false,
-    "input_names": [
-      "latent_sample"
-    ],
-    "output_names": [
-      "sample"
-    ],
-    "static_batch_size": 1,
-    "static_height": 32,
-    "static_num_channels": 4,
-    "static_width": 32
-  },
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 128,
-  "scaling_factor": 0.18215,
-  "transformers_version": null,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}

vae_decoder/model.neuron

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5b82a261ffafadf9acee949d3e5b354544ba8c6e4a5466893f05c96ea64cbbe
-size 2973404

vocab.txt

@@ -1,1124 +0,0 @@
-[PAD]
-[UNK]
-[CLS]
-[SEP]
-[MASK]
-!
-"
-#
-$
-%
-&
-'
-(
-)
-*
-+
-,
--
-.
-/
-0
-1
-2
-3
-4
-5
-6
-7
-8
-9
-:
-;
-<
-=
->
-?
-@
-[
-\
-]
-^
-_
-`
-a
-b
-c
-d
-e
-f
-g
-h
-i
-j
-k
-l
-m
-n
-o
-p
-q
-r
-s
-t
-u
-v
-w
-x
-y
-z
-|
-}
-~
-¡
-¢
-£
-¥
-§
-°
-±
-²
-³
-´
-µ
-·
-º
-½
-¿
-×
-ß
-æ
-ð
-ø
-þ
-đ
-ħ
-ı
-ł
-œ
-ɐ
-ɑ
-ɒ
-ɔ
-ə
-ɛ
-ɜ
-ɡ
-ɢ
-ɪ
-ɫ
-ɳ
-ɽ
-ɾ
-ʁ
-ʃ
-ʊ
-ʋ
-ʒ
-ʔ
-ʕ
-ʲ
-ʻ
-ʼ
-ʾ
-ʿ
-ˈ
-ˌ
-ː
-α
-β
-γ
-δ
-ε
-η
-θ
-ι
-κ
-λ
-μ
-ν
-ξ
-ο
-π
-ρ
-ς
-σ
-τ
-υ
-φ
-χ
-ψ
-ω
-а
-б
-в
-г
-д
-е
-ж
-з
-и
-к
-л
-м
-н
-о
-п
-р
-с
-т
-у
-х
-ц
-ш
-ъ
-ы
-ь
-ю
-я
-є
-א
-ב
-ג
-ה
-ו
-ז
-ח
-י
-ל
-ם
-מ
-ן
-נ
-ס
-ף
-פ
-צ
-ר
-ש
-ת
-ء
-ا
-ب
-ة
-ت
-ث
-ج
-ح
-خ
-د
-ذ
-ر
-س
-ش
-ص
-ع
-ف
-ق
-ك
-ل
-م
-ن
-ه
-و
-ي
-ܐ
-ܕ
-ܗ
-ܝ
-ܠ
-ܢ
-ܬ
-अ
-ई
-क
-ग
-ण
-त
-द
-न
-प
-ब
-म
-य
-र
-ल
-व
-स
-ह
-ा
-ि
-আ
-ল
-হ
-া
-ਅ
-ਲ
-ਹ
-ਾ
-അ
-ള
-ഹ
-ാ
-ก
-ค
-ง
-ช
-ซ
-ญ
-ฐ
-ณ
-ด
-ต
-น
-บ
-ป
-พ
-ภ
-ม
-ย
-ร
-ล
-ว
-ศ
-ษ
-ส
-ห
-อ
-ฮ
-ะ
-า
-เ
-แ
-ไ
-ა
-ბ
-გ
-დ
-ე
-ვ
-ზ
-თ
-ი
-კ
-ლ
-მ
-ნ
-ო
-პ
-ჟ
-რ
-ს
-ტ
-უ
-ფ
-ქ
-ღ
-ყ
-შ
-ჩ
-ც
-ძ
-წ
-ჭ
-ხ
-ჯ
-ჰ
-ჱ
-ჲ
-ჳ
-ჴ
-ჵ
-ჶ
-ჷ
-ჸ
-ჹ
-ჺ
-჻
-ᄃ
-ᄅ
-ᄇ
-ᄋ
-ᄌ
-ᅡ
-ᅢ
-ᅦ
-ᅧ
-ᅩ
-ᅮ
-ᅵ
-ᆨ
-ᆫ
-ᆯ
-ᆸ
-ᆼ
-ᵻ
-‐
-‑
-–
-—
-―
-‘
-’
-“
-”
-„
-†
-‡
-•
-…
-′
-″
-⁄
-₣
-₤
-€
-₹
-⅓
-⅔
-→
-−
-≡
-≤
-①
-☉
-☫
-♀
-♭
-♯
-⚳
-ⴀ
-ⴂ
-ⴃ
-ⴈ
-ⴌ
-ⴕ
-ⴟ
-〈
-〉
-〜
-あ
-い
-う
-お
-か
-き
-く
-け
-こ
-さ
-し
-す
-せ
-た
-ち
-っ
-つ
-と
-な
-に
-の
-は
-ひ
-ふ
-ほ
-ま
-み
-め
-も
-ゃ
-ゆ
-ょ
-ら
-り
-る
-れ
-わ
-を
-ん
-ァ
-ア
-ィ
-イ
-ゥ
-ウ
-ェ
-エ
-ォ
-オ
-カ
-キ
-ク
-ケ
-コ
-サ
-シ
-ス
-セ
-タ
-チ
-ッ
-ツ
-テ
-ト
-ナ
-ニ
-ネ
-ノ
-ハ
-フ
-ヘ
-マ
-ミ
-ム
-モ
-ャ
-ュ
-ョ
-ラ
-リ
-ル
-レ
-ロ
-ン
-・
-ー
-一
-七
-下
-世
-丙
-中
-主
-乃
-之
-乙
-九
-二
-云
-人
-今
-付
-作
-侗
-依
-信
-傳
-儚
-充
-光
-全
-兵
-其
-具
-円
-再
-出
-判
-前
-剛
-劇
-劉
-動
-化
-北
-华
-厂
-去
-古
-可
-台
-史
-同
-名
-君
-吳
-周
-命
-和
-咲
-善
-四
-國
-園
-圣
-在
-坂
-堤
-場
-塘
-夕
-大
-天
-夫
-女
-妙
-姚
-子
-孟
-守
-安
-宋
-完
-宗
-宝
-宫
-寝
-寺
-小
-少
-尾
-山
-岳
-川
-州
-巳
-市
-師
-平
-广
-庆
-府
-座
-廬
-建
-式
-張
-彌
-彩
-彼
-後
-御
-德
-思
-愛
-憑
-憶
-應
-懷
-战
-戦
-扈
-技
-拉
-拳
-挑
-揺
-攻
-放
-政
-散
-斯
-方
-日
-旦
-旭
-昌
-明
-星
-春
-晋
-景
-曦
-月
-望
-未
-本
-李
-村
-杜
-束
-来
-林
-桜
-梶
-棘
-椎
-楊
-楚
-榮
-橘
-機
-正
-殻
-殿
-母
-水
-汉
-沂
-沙
-河
-泗
-波
-泣
-洪
-淹
-清
-湯
-漢
-澄
-澤
-火
-灯
-灵
-灼
-焼
-熱
-物
-狐
-狸
-玄
-王
-玩
-珂
-珙
-球
-理
-琦
-琪
-瓊
-生
-田
-畢
-番
-瘡
-白
-皮
-真
-砲
-礮
-祈
-神
-祠
-秋
-空
-立
-精
-約
-絵
-織
-義
-翠
-者
-耕
-肖
-胡
-膀
-臂
-興
-良
-花
-芳
-芽
-若
-英
-藕
-藥
-蘄
-蘇
-行
-裁
-規
-覺
-观
-解
-記
-誓
-誡
-誰
-謎
-许
-谭
-豪
-豫
-費
-贵
-赤
-趙
-足
-跡
-転
-辛
-逆
-遇
-運
-過
-遠
-選
-邦
-邱
-部
-郭
-都
-酈
-里
-野
-金
-銃
-鋼
-錄
-錡
-鍵
-鐵
-钱
-铁
-關
-防
-阿
-陈
-陳
-陽
-隊
-階
-集
-雪
-雲
-霖
-霹
-靂
-韓
-願
-顯
-颜
-马
-高
-龍
-ﷲ
-ﻋ
-／
-３
-～
-##i
-##y
-##o
-##r
-##g
-##a
-##w
-##l
-##b
-##z
-##t
-##n
-##c
-##h
-##s
-##u
-##d
-##e
-##k
-##v
-##f
-##x
-##q
-##p
-##æ
-##0
-##5
-##m
-##8
-##4
-##س
-##ت
-##ا
-##ن
-##6
-##1
-##7
-##j
-##つ
-##う
-##2
-##9
-##3
-##ø
-##ล
-##ว
-##ง
-##พ
-##ไ
-##ช
-##ย
-##า
-##ร
-##თ
-##ა
-##ვ
-##რ
-##ი
-##ള
-##あ
-##ん
-##α
-##ν
-##τ
-##ο
-##κ
-##ρ
-##ω
-##ς
-##の
-##な
-##ら
-##ð
-##œ
-##ɛ
-##ł
-##η
-##μ
-##ซ
-##ル
-##シ
-##ア
-##リ
-##ス
-##ʔ
-##ल
-##ᄇ
-##ᅮ
-##ᄃ
-##ᅢ
-##β
-##ß
-##か
-##た
-##ə
-##ʻ
-##ι
-##χ
-##о
-##л
-##с
-##а
-##т
-##ы
-##и
-##в
-##к
-##з
-##ッ
-##ク
-##マ
-##ン
-##გ
-##ლ
-##ო
-##ნ
-##ː
-##ל
-##ה
-##א
-##く
-##み
-##ε
-##ξ
-##ল
-##ˈ
-##ɡ
-##ɑ
-##ɒ
-##し
-##す
-##き
-##ひ
-##と
-##đ
-##ъ
-##н
-##е
-##י
-##פ
-##イ
-##λ
-##ق
-##ع
-##د
-##ᅡ
-##ᆯ
-##ᄅ
-##ɪ
-##ค
-##ต
-##व
-##ा
-##द
-##は
-##り
-##レ
-##ー
-##ツ
-##ي
-##ش
-##و
-##م
-##º
-##ਲ
-##ਾ
-##ਹ
-##д
-##р
-##ل
-##ب
-##い
-##ち
-##ゃ
-##ʒ
-##ʃ
-##ɔ
-##ह
-##ニ
-##ウ
-##ァ
-##キ
-##ュ
-##３
-##ხ
-##ს
-##お
-##タ
-##ാ
-##ഹ
-##ɳ
-##ま
-##る
-##ะ
-##อ
-##น
-##ן
-##я
-##แ
-##ก
-##ɾ
-##ʲ
-##フ
-##უ
-##ภ
-##ด
-##ב
-##ת
-##خ
-##ラ
-##れ
-##ण
-##स
-##न
-##ه
-##ف
-##ر
-##エ
-##テ
-##ษ
-##ฐ
-##ィ
-##क
-##ノ
-##θ
-##ネ
-##��
-##δ
-##ɽ
-##ʁ
-##ტ
-##ჱ
-##ェ
-##ハ
-##υ
-##र
-##х
-##も
-##っ
-##ょ
-##に
-##γ
-##ც
-##ე
-##є
-##м
-##ܕ
-##ܝ
-##ܢ
-##ܬ
-##ณ
-##ม
-##ฮ
-##ж
-##ם
-##ء
-##ʊ
-##ई
-##め
-##მ
-##ム
-##チ
-##ᵻ
-##ˌ
-##ו
-##ף
-##წ
-##ფ
-##ャ
-##モ
-##ɐ
-##ᅦ
-##ᅩ
-##ᆨ
-##ᅵ
-##ᆸ
-##ᅧ
-##ᆼ
-##ᄋ
-##ᆫ
-##わ
-##ı
-##ქ
-##დ
-##ि
-##ჲ
-##ר
-##セ
-##オ
-##ゆ
-##せ
-##ك
-##ʿ
-##ש
-##מ
-##צ
-##п
-##г
-##カ
-##ܠ
-##ܗ
-##ܐ
-##ナ
-##ミ
-##こ
-##を
-##ψ
-##サ
-##ォ
-##π
-##ト
-##у
-##ح
-##σ
-##เ
-##ป
-##ш
-##ゥ
-##ロ
-##া
-##হ
-##ɜ
-##ة
-##ص
-##ס
-##ث
-##ჳ
-##נ
-##ذ
-##ग
-##ɫ
-##ц
-##ь
-##ю