Add tiny processor fixture for testing

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Idefics2ForConditionalGeneration"
+  ],
+  "image_token_id": 32001,
+  "model_type": "idefics2",
+  "perceiver_config": {
+    "model_type": "idefics2"
+  },
+  "text_config": {
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "vocab_size": 32003
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "idefics2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  },
+  "vocab_size": 501
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [[32000], [32001]],
+  "bos_token_id": 1,
+  "eos_token_id": [2, 32002],
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Idefics2ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Idefics2Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 980,
+    "shortest_edge": 378
+  }
+}

processor_config.json

@@ -0,0 +1,5 @@
+{
+  "chat_template": "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "image_seq_len": 64,
+  "processor_class": "Idefics2Processor"
+}

tokenizer.json

@@ -0,0 +1,723 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "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": 501,
+      "content": "<fake_token_around_image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 502,
+      "content": "<image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 503,
+      "content": "<end_of_utterance>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Prepend",
+        "prepend": "▁"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": " "
+        },
+        "content": "▁"
+      }
+    ]
+  },
+  "pre_tokenizer": null,
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 1
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<s>": {
+        "id": "<s>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<s>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "Sequence",
+    "decoders": [
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "▁"
+        },
+        "content": " "
+      },
+      {
+        "type": "ByteFallback"
+      },
+      {
+        "type": "Fuse"
+      },
+      {
+        "type": "Strip",
+        "content": " ",
+        "start": 1,
+        "stop": 0
+      }
+    ]
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<unk>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": true,
+    "byte_fallback": true,
+    "vocab": {
+      "<unk>": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "<0x00>": 3,
+      "<0x01>": 4,
+      "<0x02>": 5,
+      "<0x03>": 6,
+      "<0x04>": 7,
+      "<0x05>": 8,
+      "<0x06>": 9,
+      "<0x07>": 10,
+      "<0x08>": 11,
+      "<0x09>": 12,
+      "<0x0A>": 13,
+      "<0x0B>": 14,
+      "<0x0C>": 15,
+      "<0x0D>": 16,
+      "<0x0E>": 17,
+      "<0x0F>": 18,
+      "<0x10>": 19,
+      "<0x11>": 20,
+      "<0x12>": 21,
+      "<0x13>": 22,
+      "<0x14>": 23,
+      "<0x15>": 24,
+      "<0x16>": 25,
+      "<0x17>": 26,
+      "<0x18>": 27,
+      "<0x19>": 28,
+      "<0x1A>": 29,
+      "<0x1B>": 30,
+      "<0x1C>": 31,
+      "<0x1D>": 32,
+      "<0x1E>": 33,
+      "<0x1F>": 34,
+      "<0x20>": 35,
+      "<0x21>": 36,
+      "<0x22>": 37,
+      "<0x23>": 38,
+      "<0x24>": 39,
+      "<0x25>": 40,
+      "<0x26>": 41,
+      "<0x27>": 42,
+      "<0x28>": 43,
+      "<0x29>": 44,
+      "<0x2A>": 45,
+      "<0x2B>": 46,
+      "<0x2C>": 47,
+      "<0x2D>": 48,
+      "<0x2E>": 49,
+      "<0x2F>": 50,
+      "<0x30>": 51,
+      "<0x31>": 52,
+      "<0x32>": 53,
+      "<0x33>": 54,
+      "<0x34>": 55,
+      "<0x35>": 56,
+      "<0x36>": 57,
+      "<0x37>": 58,
+      "<0x38>": 59,
+      "<0x39>": 60,
+      "<0x3A>": 61,
+      "<0x3B>": 62,
+      "<0x3C>": 63,
+      "<0x3D>": 64,
+      "<0x3E>": 65,
+      "<0x3F>": 66,
+      "<0x40>": 67,
+      "<0x41>": 68,
+      "<0x42>": 69,
+      "<0x43>": 70,
+      "<0x44>": 71,
+      "<0x45>": 72,
+      "<0x46>": 73,
+      "<0x47>": 74,
+      "<0x48>": 75,
+      "<0x49>": 76,
+      "<0x4A>": 77,
+      "<0x4B>": 78,
+      "<0x4C>": 79,
+      "<0x4D>": 80,
+      "<0x4E>": 81,
+      "<0x4F>": 82,
+      "<0x50>": 83,
+      "<0x51>": 84,
+      "<0x52>": 85,
+      "<0x53>": 86,
+      "<0x54>": 87,
+      "<0x55>": 88,
+      "<0x56>": 89,
+      "<0x57>": 90,
+      "<0x58>": 91,
+      "<0x59>": 92,
+      "<0x5A>": 93,
+      "<0x5B>": 94,
+      "<0x5C>": 95,
+      "<0x5D>": 96,
+      "<0x5E>": 97,
+      "<0x5F>": 98,
+      "<0x60>": 99,
+      "<0x61>": 100,
+      "<0x62>": 101,
+      "<0x63>": 102,
+      "<0x64>": 103,
+      "<0x65>": 104,
+      "<0x66>": 105,
+      "<0x67>": 106,
+      "<0x68>": 107,
+      "<0x69>": 108,
+      "<0x6A>": 109,
+      "<0x6B>": 110,
+      "<0x6C>": 111,
+      "<0x6D>": 112,
+      "<0x6E>": 113,
+      "<0x6F>": 114,
+      "<0x70>": 115,
+      "<0x71>": 116,
+      "<0x72>": 117,
+      "<0x73>": 118,
+      "<0x74>": 119,
+      "<0x75>": 120,
+      "<0x76>": 121,
+      "<0x77>": 122,
+      "<0x78>": 123,
+      "<0x79>": 124,
+      "<0x7A>": 125,
+      "<0x7B>": 126,
+      "<0x7C>": 127,
+      "<0x7D>": 128,
+      "<0x7E>": 129,
+      "<0x7F>": 130,
+      "<0x80>": 131,
+      "<0x81>": 132,
+      "<0x82>": 133,
+      "<0x83>": 134,
+      "<0x84>": 135,
+      "<0x85>": 136,
+      "<0x86>": 137,
+      "<0x87>": 138,
+      "<0x88>": 139,
+      "<0x89>": 140,
+      "<0x8A>": 141,
+      "<0x8B>": 142,
+      "<0x8C>": 143,
+      "<0x8D>": 144,
+      "<0x8E>": 145,
+      "<0x8F>": 146,
+      "<0x90>": 147,
+      "<0x91>": 148,
+      "<0x92>": 149,
+      "<0x93>": 150,
+      "<0x94>": 151,
+      "<0x95>": 152,
+      "<0x96>": 153,
+      "<0x97>": 154,
+      "<0x98>": 155,
+      "<0x99>": 156,
+      "<0x9A>": 157,
+      "<0x9B>": 158,
+      "<0x9C>": 159,
+      "<0x9D>": 160,
+      "<0x9E>": 161,
+      "<0x9F>": 162,
+      "<0xA0>": 163,
+      "<0xA1>": 164,
+      "<0xA2>": 165,
+      "<0xA3>": 166,
+      "<0xA4>": 167,
+      "<0xA5>": 168,
+      "<0xA6>": 169,
+      "<0xA7>": 170,
+      "<0xA8>": 171,
+      "<0xA9>": 172,
+      "<0xAA>": 173,
+      "<0xAB>": 174,
+      "<0xAC>": 175,
+      "<0xAD>": 176,
+      "<0xAE>": 177,
+      "<0xAF>": 178,
+      "<0xB0>": 179,
+      "<0xB1>": 180,
+      "<0xB2>": 181,
+      "<0xB3>": 182,
+      "<0xB4>": 183,
+      "<0xB5>": 184,
+      "<0xB6>": 185,
+      "<0xB7>": 186,
+      "<0xB8>": 187,
+      "<0xB9>": 188,
+      "<0xBA>": 189,
+      "<0xBB>": 190,
+      "<0xBC>": 191,
+      "<0xBD>": 192,
+      "<0xBE>": 193,
+      "<0xBF>": 194,
+      "<0xC0>": 195,
+      "<0xC1>": 196,
+      "<0xC2>": 197,
+      "<0xC3>": 198,
+      "<0xC4>": 199,
+      "<0xC5>": 200,
+      "<0xC6>": 201,
+      "<0xC7>": 202,
+      "<0xC8>": 203,
+      "<0xC9>": 204,
+      "<0xCA>": 205,
+      "<0xCB>": 206,
+      "<0xCC>": 207,
+      "<0xCD>": 208,
+      "<0xCE>": 209,
+      "<0xCF>": 210,
+      "<0xD0>": 211,
+      "<0xD1>": 212,
+      "<0xD2>": 213,
+      "<0xD3>": 214,
+      "<0xD4>": 215,
+      "<0xD5>": 216,
+      "<0xD6>": 217,
+      "<0xD7>": 218,
+      "<0xD8>": 219,
+      "<0xD9>": 220,
+      "<0xDA>": 221,
+      "<0xDB>": 222,
+      "<0xDC>": 223,
+      "<0xDD>": 224,
+      "<0xDE>": 225,
+      "<0xDF>": 226,
+      "<0xE0>": 227,
+      "<0xE1>": 228,
+      "<0xE2>": 229,
+      "<0xE3>": 230,
+      "<0xE4>": 231,
+      "<0xE5>": 232,
+      "<0xE6>": 233,
+      "<0xE7>": 234,
+      "<0xE8>": 235,
+      "<0xE9>": 236,
+      "<0xEA>": 237,
+      "<0xEB>": 238,
+      "<0xEC>": 239,
+      "<0xED>": 240,
+      "<0xEE>": 241,
+      "<0xEF>": 242,
+      "<0xF0>": 243,
+      "<0xF1>": 244,
+      "<0xF2>": 245,
+      "<0xF3>": 246,
+      "<0xF4>": 247,
+      "<0xF5>": 248,
+      "<0xF6>": 249,
+      "<0xF7>": 250,
+      "<0xF8>": 251,
+      "<0xF9>": 252,
+      "<0xFA>": 253,
+      "<0xFB>": 254,
+      "<0xFC>": 255,
+      "<0xFD>": 256,
+      "<0xFE>": 257,
+      "<0xFF>": 258,
+      "▁▁": 259,
+      "▁▁▁▁": 260,
+      "▁t": 261,
+      "in": 262,
+      "er": 263,
+      "▁a": 264,
+      "he": 265,
+      "on": 266,
+      "re": 267,
+      "▁s": 268,
+      "en": 269,
+      "at": 270,
+      "or": 271,
+      "▁the": 272,
+      "▁▁▁▁▁▁▁▁": 273,
+      "es": 274,
+      "▁w": 275,
+      "an": 276,
+      "▁c": 277,
+      "is": 278,
+      "it": 279,
+      "ou": 280,
+      "▁d": 281,
+      "al": 282,
+      "ar": 283,
+      "▁p": 284,
+      "▁f": 285,
+      "ed": 286,
+      "▁b": 287,
+      "ing": 288,
+      "▁o": 289,
+      "▁m": 290,
+      "le": 291,
+      "nd": 292,
+      "as": 293,
+      "ic": 294,
+      "▁h": 295,
+      "ion": 296,
+      "▁in": 297,
+      "▁to": 298,
+      "et": 299,
+      "om": 300,
+      "el": 301,
+      "▁of": 302,
+      "st": 303,
+      "▁and": 304,
+      "▁l": 305,
+      "▁th": 306,
+      "▁n": 307,
+      "ent": 308,
+      "il": 309,
+      "ct": 310,
+      "ro": 311,
+      "▁re": 312,
+      "id": 313,
+      "am": 314,
+      "▁I": 315,
+      "ad": 316,
+      "▁e": 317,
+      "▁S": 318,
+      "▁g": 319,
+      "▁T": 320,
+      "im": 321,
+      "ot": 322,
+      "ac": 323,
+      "ur": 324,
+      "▁(": 325,
+      "ig": 326,
+      "▁=": 327,
+      "ol": 328,
+      "ut": 329,
+      "▁A": 330,
+      "se": 331,
+      "▁u": 332,
+      "ve": 333,
+      "▁C": 334,
+      "if": 335,
+      "ow": 336,
+      "▁y": 337,
+      "ch": 338,
+      "ay": 339,
+      "▁de": 340,
+      "▁st": 341,
+      "▁|": 342,
+      "ver": 343,
+      ");": 344,
+      "▁\"": 345,
+      "ly": 346,
+      "▁be": 347,
+      "**": 348,
+      "▁is": 349,
+      "od": 350,
+      "▁M": 351,
+      "ation": 352,
+      "ul": 353,
+      "▁for": 354,
+      "▁▁▁▁▁": 355,
+      "▁on": 356,
+      "ag": 357,
+      "ce": 358,
+      "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 359,
+      "ter": 360,
+      "ir": 361,
+      "th": 362,
+      "▁v": 363,
+      "qu": 364,
+      "▁B": 365,
+      "em": 366,
+      "▁P": 367,
+      "▁you": 368,
+      "▁that": 369,
+      "un": 370,
+      "▁{": 371,
+      "ith": 372,
+      "ri": 373,
+      "est": 374,
+      "ab": 375,
+      "--": 376,
+      "ap": 377,
+      "▁it": 378,
+      "▁con": 379,
+      "ate": 380,
+      "us": 381,
+      "▁H": 382,
+      "um": 383,
+      "▁D": 384,
+      "os": 385,
+      "pe": 386,
+      "▁-": 387,
+      "▁wh": 388,
+      "▁al": 389,
+      "▁as": 390,
+      "and": 391,
+      "ist": 392,
+      "▁L": 393,
+      "▁W": 394,
+      "▁with": 395,
+      "▁an": 396,
+      "ere": 397,
+      "▁*": 398,
+      "▁R": 399,
+      "▁he": 400,
+      "▁F": 401,
+      "oc": 402,
+      "▁was": 403,
+      "ers": 404,
+      "ke": 405,
+      "out": 406,
+      "ht": 407,
+      "▁r": 408,
+      "ess": 409,
+      "op": 410,
+      "res": 411,
+      "ie": 412,
+      "▁E": 413,
+      "▁\\": 414,
+      "▁The": 415,
+      "end": 416,
+      "ld": 417,
+      "▁N": 418,
+      "ort": 419,
+      "▁G": 420,
+      "//": 421,
+      "▁#": 422,
+      "our": 423,
+      "te": 424,
+      "ill": 425,
+      "ain": 426,
+      "▁se": 427,
+      "▁▁▁▁▁▁": 428,
+      "▁$": 429,
+      "▁pro": 430,
+      "ore": 431,
+      "▁com": 432,
+      "ame": 433,
+      "tr": 434,
+      "▁ne": 435,
+      "rom": 436,
+      "ub": 437,
+      "▁at": 438,
+      "▁ex": 439,
+      "ant": 440,
+      "ue": 441,
+      "▁or": 442,
+      "▁}": 443,
+      "art": 444,
+      "ction": 445,
+      "▁k": 446,
+      "pt": 447,
+      "nt": 448,
+      "iv": 449,
+      "de": 450,
+      "▁O": 451,
+      "pl": 452,
+      "urn": 453,
+      "ight": 454,
+      "all": 455,
+      "▁this": 456,
+      "ser": 457,
+      "ave": 458,
+      "▁not": 459,
+      "▁are": 460,
+      "▁j": 461,
+      "▁le": 462,
+      "iz": 463,
+      "▁'": 464,
+      "age": 465,
+      "ment": 466,
+      "▁tr": 467,
+      "ack": 468,
+      "ust": 469,
+      "()": 470,
+      "->": 471,
+      "ity": 472,
+      "ine": 473,
+      "ould": 474,
+      "▁J": 475,
+      "og": 476,
+      "▁from": 477,
+      "▁we": 478,
+      "ell": 479,
+      "▁sh": 480,
+      "▁en": 481,
+      "ure": 482,
+      "port": 483,
+      "▁ch": 484,
+      "ne": 485,
+      "▁by": 486,
+      "per": 487,
+      "ard": 488,
+      "ass": 489,
+      "ge": 490,
+      "ak": 491,
+      "are": 492,
+      "ok": 493,
+      "av": 494,
+      "ive": 495,
+      "ff": 496,
+      "ies": 497,
+      "ath": 498,
+      "turn": 499,
+      "▁": 500
+    },
+    "merges": [
+      "▁t he",
+      "▁ in",
+      "▁a nd",
+      "▁ and",
+      "▁ th",
+      "▁ re",
+      "▁ de",
+      "▁ st",
+      "▁ is",
+      "at ion",
+      "▁f or",
+      "▁ on",
+      "▁y ou",
+      "▁th at",
+      "▁ it",
+      "▁c on",
+      "▁ al",
+      "▁ as",
+      "▁w ith",
+      "▁ an",
+      "▁ he",
+      "▁w as",
+      "▁T he",
+      "▁ se",
+      "▁p ro",
+      "▁c om",
+      "▁ ne",
+      "▁ at",
+      "▁ or",
+      "ct ion",
+      "ig ht",
+      "▁th is",
+      "▁n ot",
+      "▁a re",
+      "▁ are",
+      "▁ le",
+      "▁ tr",
+      "ou ld",
+      "▁f rom",
+      "▁ en",
+      "▁ ch",
+      "▁ ▁",
+      "▁▁ ▁▁",
+      "▁▁ ▁▁▁▁▁▁",
+      "▁▁▁▁ ▁▁▁▁",
+      "▁▁▁▁▁▁ ▁▁",
+      "▁▁▁▁ ▁",
+      "▁ ▁▁▁▁",
+      "▁▁▁▁▁▁▁▁ ▁▁▁▁▁▁▁▁",
+      "▁▁ ▁▁▁▁",
+      "▁▁▁▁ ▁▁",
+      "▁▁▁▁▁ ▁",
+      "▁ ▁▁▁▁▁"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,71 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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
+    },
+    "32000": {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "processor_class": "Idefics2Processor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}