Add tiny processor fixture for testing

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "Owlv2ForObjectDetection"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "owlv2",
+  "projection_dim": 512,
+  "text_config": {
+    "model_type": "owlv2_text_model"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "vision_config": {
+    "image_size": 960,
+    "model_type": "owlv2_vision_model",
+    "patch_size": 16
+  },
+  "vocab_size": 502
+}

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Owlv2ImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "Owlv2Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 960,
+    "width": 960
+  }
+}

tokenizer.json

@@ -0,0 +1,592 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 500,
+      "special": true,
+      "content": "<|startoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true
+    },
+    {
+      "id": 501,
+      "special": true,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "NFC"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "Regex": "\\s+"
+        },
+        "content": " "
+      },
+      {
+        "type": "Lowercase"
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Sequence",
+    "pretokenizers": [
+      {
+        "type": "Split",
+        "pattern": {
+          "Regex": "<\\|startoftext\\|>|<\\|endoftext\\|>|'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
+        },
+        "behavior": "Removed",
+        "invert": true
+      },
+      {
+        "type": "ByteLevel",
+        "add_prefix_space": false,
+        "trim_offsets": true
+      }
+    ]
+  },
+  "post_processor": {
+    "type": "RobertaProcessing",
+    "sep": [
+      "<|endoftext|>",
+      49407
+    ],
+    "cls": [
+      "<|startoftext|>",
+      49406
+    ],
+    "trim_offsets": false,
+    "add_prefix_space": false
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<|endoftext|>",
+    "continuing_subword_prefix": "",
+    "end_of_word_suffix": "</w>",
+    "fuse_unk": false,
+    "vocab": {
+      "!": 0,
+      "\"": 1,
+      "#": 2,
+      "$": 3,
+      "%": 4,
+      "&": 5,
+      "'": 6,
+      "(": 7,
+      ")": 8,
+      "*": 9,
+      "+": 10,
+      ",": 11,
+      "-": 12,
+      ".": 13,
+      "/": 14,
+      "0": 15,
+      "1": 16,
+      "2": 17,
+      "3": 18,
+      "4": 19,
+      "5": 20,
+      "6": 21,
+      "7": 22,
+      "8": 23,
+      "9": 24,
+      ":": 25,
+      ";": 26,
+      "<": 27,
+      "=": 28,
+      ">": 29,
+      "?": 30,
+      "@": 31,
+      "A": 32,
+      "B": 33,
+      "C": 34,
+      "D": 35,
+      "E": 36,
+      "F": 37,
+      "G": 38,
+      "H": 39,
+      "I": 40,
+      "J": 41,
+      "K": 42,
+      "L": 43,
+      "M": 44,
+      "N": 45,
+      "O": 46,
+      "P": 47,
+      "Q": 48,
+      "R": 49,
+      "S": 50,
+      "T": 51,
+      "U": 52,
+      "V": 53,
+      "W": 54,
+      "X": 55,
+      "Y": 56,
+      "Z": 57,
+      "[": 58,
+      "\\": 59,
+      "]": 60,
+      "^": 61,
+      "_": 62,
+      "`": 63,
+      "a": 64,
+      "b": 65,
+      "c": 66,
+      "d": 67,
+      "e": 68,
+      "f": 69,
+      "g": 70,
+      "h": 71,
+      "i": 72,
+      "j": 73,
+      "k": 74,
+      "l": 75,
+      "m": 76,
+      "n": 77,
+      "o": 78,
+      "p": 79,
+      "q": 80,
+      "r": 81,
+      "s": 82,
+      "t": 83,
+      "u": 84,
+      "v": 85,
+      "w": 86,
+      "x": 87,
+      "y": 88,
+      "z": 89,
+      "{": 90,
+      "|": 91,
+      "}": 92,
+      "~": 93,
+      "¡": 94,
+      "¢": 95,
+      "£": 96,
+      "¤": 97,
+      "¥": 98,
+      "¦": 99,
+      "§": 100,
+      "¨": 101,
+      "©": 102,
+      "ª": 103,
+      "«": 104,
+      "¬": 105,
+      "®": 106,
+      "¯": 107,
+      "°": 108,
+      "±": 109,
+      "²": 110,
+      "³": 111,
+      "´": 112,
+      "µ": 113,
+      "¶": 114,
+      "·": 115,
+      "¸": 116,
+      "¹": 117,
+      "º": 118,
+      "»": 119,
+      "¼": 120,
+      "½": 121,
+      "¾": 122,
+      "¿": 123,
+      "À": 124,
+      "Á": 125,
+      "Â": 126,
+      "Ã": 127,
+      "Ä": 128,
+      "Å": 129,
+      "Æ": 130,
+      "Ç": 131,
+      "È": 132,
+      "É": 133,
+      "Ê": 134,
+      "Ë": 135,
+      "Ì": 136,
+      "Í": 137,
+      "Î": 138,
+      "Ï": 139,
+      "Ð": 140,
+      "Ñ": 141,
+      "Ò": 142,
+      "Ó": 143,
+      "Ô": 144,
+      "Õ": 145,
+      "Ö": 146,
+      "×": 147,
+      "Ø": 148,
+      "Ù": 149,
+      "Ú": 150,
+      "Û": 151,
+      "Ü": 152,
+      "Ý": 153,
+      "Þ": 154,
+      "ß": 155,
+      "à": 156,
+      "á": 157,
+      "â": 158,
+      "ã": 159,
+      "ä": 160,
+      "å": 161,
+      "æ": 162,
+      "ç": 163,
+      "è": 164,
+      "é": 165,
+      "ê": 166,
+      "ë": 167,
+      "ì": 168,
+      "í": 169,
+      "î": 170,
+      "ï": 171,
+      "ð": 172,
+      "ñ": 173,
+      "ò": 174,
+      "ó": 175,
+      "ô": 176,
+      "õ": 177,
+      "ö": 178,
+      "÷": 179,
+      "ø": 180,
+      "ù": 181,
+      "ú": 182,
+      "û": 183,
+      "ü": 184,
+      "ý": 185,
+      "þ": 186,
+      "ÿ": 187,
+      "Ā": 188,
+      "ā": 189,
+      "Ă": 190,
+      "ă": 191,
+      "Ą": 192,
+      "ą": 193,
+      "Ć": 194,
+      "ć": 195,
+      "Ĉ": 196,
+      "ĉ": 197,
+      "Ċ": 198,
+      "ċ": 199,
+      "Č": 200,
+      "č": 201,
+      "Ď": 202,
+      "ď": 203,
+      "Đ": 204,
+      "đ": 205,
+      "Ē": 206,
+      "ē": 207,
+      "Ĕ": 208,
+      "ĕ": 209,
+      "Ė": 210,
+      "ė": 211,
+      "Ę": 212,
+      "ę": 213,
+      "Ě": 214,
+      "ě": 215,
+      "Ĝ": 216,
+      "ĝ": 217,
+      "Ğ": 218,
+      "ğ": 219,
+      "Ġ": 220,
+      "ġ": 221,
+      "Ģ": 222,
+      "ģ": 223,
+      "Ĥ": 224,
+      "ĥ": 225,
+      "Ħ": 226,
+      "ħ": 227,
+      "Ĩ": 228,
+      "ĩ": 229,
+      "Ī": 230,
+      "ī": 231,
+      "Ĭ": 232,
+      "ĭ": 233,
+      "Į": 234,
+      "į": 235,
+      "İ": 236,
+      "ı": 237,
+      "IJ": 238,
+      "ij": 239,
+      "Ĵ": 240,
+      "ĵ": 241,
+      "Ķ": 242,
+      "ķ": 243,
+      "ĸ": 244,
+      "Ĺ": 245,
+      "ĺ": 246,
+      "Ļ": 247,
+      "ļ": 248,
+      "Ľ": 249,
+      "ľ": 250,
+      "Ŀ": 251,
+      "ŀ": 252,
+      "Ł": 253,
+      "ł": 254,
+      "Ń": 255,
+      "!</w>": 256,
+      "\"</w>": 257,
+      "#</w>": 258,
+      "$</w>": 259,
+      "%</w>": 260,
+      "&</w>": 261,
+      "'</w>": 262,
+      "(</w>": 263,
+      ")</w>": 264,
+      "*</w>": 265,
+      "+</w>": 266,
+      ",</w>": 267,
+      "-</w>": 268,
+      ".</w>": 269,
+      "/</w>": 270,
+      "0</w>": 271,
+      "1</w>": 272,
+      "2</w>": 273,
+      "3</w>": 274,
+      "4</w>": 275,
+      "5</w>": 276,
+      "6</w>": 277,
+      "7</w>": 278,
+      "8</w>": 279,
+      "9</w>": 280,
+      ":</w>": 281,
+      ";</w>": 282,
+      "<</w>": 283,
+      "=</w>": 284,
+      "></w>": 285,
+      "?</w>": 286,
+      "@</w>": 287,
+      "A</w>": 288,
+      "B</w>": 289,
+      "C</w>": 290,
+      "D</w>": 291,
+      "E</w>": 292,
+      "F</w>": 293,
+      "G</w>": 294,
+      "H</w>": 295,
+      "I</w>": 296,
+      "J</w>": 297,
+      "K</w>": 298,
+      "L</w>": 299,
+      "M</w>": 300,
+      "N</w>": 301,
+      "O</w>": 302,
+      "P</w>": 303,
+      "Q</w>": 304,
+      "R</w>": 305,
+      "S</w>": 306,
+      "T</w>": 307,
+      "U</w>": 308,
+      "V</w>": 309,
+      "W</w>": 310,
+      "X</w>": 311,
+      "Y</w>": 312,
+      "Z</w>": 313,
+      "[</w>": 314,
+      "\\</w>": 315,
+      "]</w>": 316,
+      "^</w>": 317,
+      "_</w>": 318,
+      "`</w>": 319,
+      "a</w>": 320,
+      "b</w>": 321,
+      "c</w>": 322,
+      "d</w>": 323,
+      "e</w>": 324,
+      "f</w>": 325,
+      "g</w>": 326,
+      "h</w>": 327,
+      "i</w>": 328,
+      "j</w>": 329,
+      "k</w>": 330,
+      "l</w>": 331,
+      "m</w>": 332,
+      "n</w>": 333,
+      "o</w>": 334,
+      "p</w>": 335,
+      "q</w>": 336,
+      "r</w>": 337,
+      "s</w>": 338,
+      "t</w>": 339,
+      "u</w>": 340,
+      "v</w>": 341,
+      "w</w>": 342,
+      "x</w>": 343,
+      "y</w>": 344,
+      "z</w>": 345,
+      "{</w>": 346,
+      "|</w>": 347,
+      "}</w>": 348,
+      "~</w>": 349,
+      "¡</w>": 350,
+      "¢</w>": 351,
+      "£</w>": 352,
+      "¤</w>": 353,
+      "¥</w>": 354,
+      "¦</w>": 355,
+      "§</w>": 356,
+      "¨</w>": 357,
+      "©</w>": 358,
+      "ª</w>": 359,
+      "«</w>": 360,
+      "¬</w>": 361,
+      "®</w>": 362,
+      "¯</w>": 363,
+      "°</w>": 364,
+      "±</w>": 365,
+      "²</w>": 366,
+      "³</w>": 367,
+      "´</w>": 368,
+      "µ</w>": 369,
+      "¶</w>": 370,
+      "·</w>": 371,
+      "¸</w>": 372,
+      "¹</w>": 373,
+      "º</w>": 374,
+      "»</w>": 375,
+      "¼</w>": 376,
+      "½</w>": 377,
+      "¾</w>": 378,
+      "¿</w>": 379,
+      "À</w>": 380,
+      "Á</w>": 381,
+      "Â</w>": 382,
+      "Ã</w>": 383,
+      "Ä</w>": 384,
+      "Å</w>": 385,
+      "Æ</w>": 386,
+      "Ç</w>": 387,
+      "È</w>": 388,
+      "É</w>": 389,
+      "Ê</w>": 390,
+      "Ë</w>": 391,
+      "Ì</w>": 392,
+      "Í</w>": 393,
+      "Î</w>": 394,
+      "Ï</w>": 395,
+      "Ð</w>": 396,
+      "Ñ</w>": 397,
+      "Ò</w>": 398,
+      "Ó</w>": 399,
+      "Ô</w>": 400,
+      "Õ</w>": 401,
+      "Ö</w>": 402,
+      "×</w>": 403,
+      "Ø</w>": 404,
+      "Ù</w>": 405,
+      "Ú</w>": 406,
+      "Û</w>": 407,
+      "Ü</w>": 408,
+      "Ý</w>": 409,
+      "Þ</w>": 410,
+      "ß</w>": 411,
+      "à</w>": 412,
+      "á</w>": 413,
+      "â</w>": 414,
+      "ã</w>": 415,
+      "ä</w>": 416,
+      "å</w>": 417,
+      "æ</w>": 418,
+      "ç</w>": 419,
+      "è</w>": 420,
+      "é</w>": 421,
+      "ê</w>": 422,
+      "ë</w>": 423,
+      "ì</w>": 424,
+      "í</w>": 425,
+      "î</w>": 426,
+      "ï</w>": 427,
+      "ð</w>": 428,
+      "ñ</w>": 429,
+      "ò</w>": 430,
+      "ó</w>": 431,
+      "ô</w>": 432,
+      "õ</w>": 433,
+      "ö</w>": 434,
+      "÷</w>": 435,
+      "ø</w>": 436,
+      "ù</w>": 437,
+      "ú</w>": 438,
+      "û</w>": 439,
+      "ü</w>": 440,
+      "ý</w>": 441,
+      "þ</w>": 442,
+      "ÿ</w>": 443,
+      "Ā</w>": 444,
+      "ā</w>": 445,
+      "Ă</w>": 446,
+      "ă</w>": 447,
+      "Ą</w>": 448,
+      "ą</w>": 449,
+      "Ć</w>": 450,
+      "ć</w>": 451,
+      "Ĉ</w>": 452,
+      "ĉ</w>": 453,
+      "Ċ</w>": 454,
+      "ċ</w>": 455,
+      "Č</w>": 456,
+      "č</w>": 457,
+      "Ď</w>": 458,
+      "ď</w>": 459,
+      "Đ</w>": 460,
+      "đ</w>": 461,
+      "Ē</w>": 462,
+      "ē</w>": 463,
+      "Ĕ</w>": 464,
+      "ĕ</w>": 465,
+      "Ė</w>": 466,
+      "ė</w>": 467,
+      "Ę</w>": 468,
+      "ę</w>": 469,
+      "Ě</w>": 470,
+      "ě</w>": 471,
+      "Ĝ</w>": 472,
+      "ĝ</w>": 473,
+      "Ğ</w>": 474,
+      "ğ</w>": 475,
+      "Ġ</w>": 476,
+      "ġ</w>": 477,
+      "Ģ</w>": 478,
+      "ģ</w>": 479,
+      "Ĥ</w>": 480,
+      "ĥ</w>": 481,
+      "Ħ</w>": 482,
+      "ħ</w>": 483,
+      "Ĩ</w>": 484,
+      "ĩ</w>": 485,
+      "Ī</w>": 486,
+      "ī</w>": 487,
+      "Ĭ</w>": 488,
+      "ĭ</w>": 489,
+      "Į</w>": 490,
+      "į</w>": 491,
+      "İ</w>": 492,
+      "ı</w>": 493,
+      "IJ</w>": 494,
+      "ij</w>": 495,
+      "Ĵ</w>": 496,
+      "ĵ</w>": 497,
+      "Ķ</w>": 498,
+      "ķ</w>": 499,
+      "<|startoftext|>": 500,
+      "<|endoftext|>": 501
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 16,
+  "pad_token": "!",
+  "processor_class": "Owlv2Processor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}