Upload CustomViltForQuestionAnswering

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,892 @@
+{
+  "architectures": [
+    "CustomViltForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "two",
+    "1": "white",
+    "2": "red",
+    "3": "blue",
+    "4": "green",
+    "5": "black",
+    "6": "three",
+    "7": "brown",
+    "8": "cat",
+    "9": "yellow",
+    "10": "dog",
+    "11": "bus",
+    "12": "airplane",
+    "13": "train",
+    "14": "room",
+    "15": "four",
+    "16": "orange",
+    "17": "bear",
+    "18": "gray",
+    "19": "truck",
+    "20": "giraffe",
+    "21": "elephant",
+    "22": "pizza",
+    "23": "bird",
+    "24": "kitchen",
+    "25": "bathroom",
+    "26": "giraffes",
+    "27": "horse",
+    "28": "motorcycle",
+    "29": "plate",
+    "30": "zebra",
+    "31": "bicycle",
+    "32": "clock",
+    "33": "car",
+    "34": "cake",
+    "35": "one",
+    "36": "purple",
+    "37": "boat",
+    "38": "zebras",
+    "39": "horses",
+    "40": "hydrant",
+    "41": "bed",
+    "42": "ball",
+    "43": "vase",
+    "44": "sandwich",
+    "45": "kite",
+    "46": "sheep",
+    "47": "elephants",
+    "48": "bat",
+    "49": "umbrella",
+    "50": "cow",
+    "51": "bowl",
+    "52": "cows",
+    "53": "phone",
+    "54": "cars",
+    "55": "five",
+    "56": "toilet",
+    "57": "cats",
+    "58": "buses",
+    "59": "computer",
+    "60": "bench",
+    "61": "boats",
+    "62": "jet",
+    "63": "birds",
+    "64": "skis",
+    "65": "bears",
+    "66": "tower",
+    "67": "kites",
+    "68": "dogs",
+    "69": "frisbee",
+    "70": "airplanes",
+    "71": "laptop",
+    "72": "motorcycles",
+    "73": "skateboard",
+    "74": "mirror",
+    "75": "chair",
+    "76": "box",
+    "77": "donut",
+    "78": "road",
+    "79": "building",
+    "80": "picture",
+    "81": "refrigerator",
+    "82": "sink",
+    "83": "window",
+    "84": "meal",
+    "85": "donuts",
+    "86": "surfboard",
+    "87": "bicycles",
+    "88": "tie",
+    "89": "desk",
+    "90": "oven",
+    "91": "banana",
+    "92": "flowers",
+    "93": "suitcase",
+    "94": "hat",
+    "95": "trains",
+    "96": "grass",
+    "97": "snowboard",
+    "98": "hill",
+    "99": "bedroom",
+    "100": "umbrellas",
+    "101": "bananas",
+    "102": "six",
+    "103": "engine",
+    "104": "trucks",
+    "105": "kitten",
+    "106": "street",
+    "107": "beach",
+    "108": "tree",
+    "109": "mountain",
+    "110": "pizzas",
+    "111": "station",
+    "112": "carriage",
+    "113": "door",
+    "114": "vegetables",
+    "115": "shirt",
+    "116": "tray",
+    "117": "cart",
+    "118": "wall",
+    "119": "fruit",
+    "120": "glasses",
+    "121": "dish",
+    "122": "vases",
+    "123": "airliner",
+    "124": "bag",
+    "125": "house",
+    "126": "cellphone",
+    "127": "toy",
+    "128": "vehicle",
+    "129": "store",
+    "130": "restaurant",
+    "131": "container",
+    "132": "pan",
+    "133": "jets",
+    "134": "sign",
+    "135": "pen",
+    "136": "computers",
+    "137": "counter",
+    "138": "suitcases",
+    "139": "boards",
+    "140": "knife",
+    "141": "racquet",
+    "142": "basket",
+    "143": "luggage",
+    "144": "plant",
+    "145": "apple",
+    "146": "phones",
+    "147": "helmet",
+    "148": "benches",
+    "149": "bottle",
+    "150": "cup",
+    "151": "office",
+    "152": "surfboards",
+    "153": "wine",
+    "154": "puppy",
+    "155": "sandwiches",
+    "156": "chairs",
+    "157": "sun",
+    "158": "bath",
+    "159": "flower",
+    "160": "beds",
+    "161": "laptops",
+    "162": "seven",
+    "163": "stove",
+    "164": "statue",
+    "165": "blender",
+    "166": "couch",
+    "167": "toothbrush",
+    "168": "sky",
+    "169": "plates",
+    "170": "scooter",
+    "171": "scissors",
+    "172": "camera",
+    "173": "oranges",
+    "174": "apples",
+    "175": "cattle",
+    "176": "airport",
+    "177": "keyboard",
+    "178": "shop",
+    "179": "table",
+    "180": "zoo",
+    "181": "fridge",
+    "182": "suit",
+    "183": "sidewalk",
+    "184": "vehicles",
+    "185": "trees",
+    "186": "pole",
+    "187": "ski",
+    "188": "trunk",
+    "189": "hillside",
+    "190": "mouse",
+    "191": "rail",
+    "192": "tracks",
+    "193": "locomotive",
+    "194": "pot",
+    "195": "restroom",
+    "196": "river",
+    "197": "shower",
+    "198": "fork",
+    "199": "goats",
+    "200": "machine",
+    "201": "vest",
+    "202": "ramp",
+    "203": "clocks",
+    "204": "salad",
+    "205": "bull",
+    "206": "carrots",
+    "207": "device",
+    "208": "dinner",
+    "209": "shelf",
+    "210": "parrot",
+    "211": "fruits",
+    "212": "duck",
+    "213": "dessert",
+    "214": "glove",
+    "215": "seagull",
+    "216": "equipment",
+    "217": "bags",
+    "218": "toilets",
+    "219": "ducks",
+    "220": "jacket",
+    "221": "buildings",
+    "222": "chocolate",
+    "223": "ship",
+    "224": "backpack",
+    "225": "photograph",
+    "226": "garage",
+    "227": "floor",
+    "228": "bread",
+    "229": "fence",
+    "230": "cakes",
+    "231": "candles",
+    "232": "broccoli",
+    "233": "pool",
+    "234": "tub",
+    "235": "drink",
+    "236": "bridge",
+    "237": "lamp",
+    "238": "screen",
+    "239": "poles",
+    "240": "wagon",
+    "241": "stall",
+    "242": "goat",
+    "243": "scene",
+    "244": "skateboards",
+    "245": "leaves",
+    "246": "cabinet",
+    "247": "cage",
+    "248": "lunch",
+    "249": "boxes",
+    "250": "lamb",
+    "251": "urinals",
+    "252": "meat",
+    "253": "pin",
+    "254": "pictures",
+    "255": "towels",
+    "256": "tv",
+    "257": "pie",
+    "258": "carrot",
+    "259": "breakfast",
+    "260": "mountains",
+    "261": "toothbrushes",
+    "262": "sculpture",
+    "263": "ties",
+    "264": "remote",
+    "265": "pastry",
+    "266": "dishes",
+    "267": "painting",
+    "268": "containers",
+    "269": "subway",
+    "270": "track",
+    "271": "sunglasses",
+    "272": "eight",
+    "273": "case",
+    "274": "garden",
+    "275": "bathtub",
+    "276": "furniture",
+    "277": "plants",
+    "278": "spoon",
+    "279": "helicopter",
+    "280": "glass",
+    "281": "dress",
+    "282": "hay",
+    "283": "remotes",
+    "284": "gear",
+    "285": "flag",
+    "286": "lambs",
+    "287": "toys",
+    "288": "hats",
+    "289": "monkey",
+    "290": "seagulls",
+    "291": "ten",
+    "292": "cheese",
+    "293": "owl",
+    "294": "nine",
+    "295": "seat",
+    "296": "stadium",
+    "297": "trolley",
+    "298": "sailboats",
+    "299": "hose",
+    "300": "fish",
+    "301": "drinks",
+    "302": "beer",
+    "303": "platter",
+    "304": "cargo",
+    "305": "entree",
+    "306": "jar",
+    "307": "uniform",
+    "308": "snack",
+    "309": "calf",
+    "310": "slice",
+    "311": "appliances",
+    "312": "pastries",
+    "313": "museum",
+    "314": "clothes",
+    "315": "ocean",
+    "316": "sailboat",
+    "317": "tablet",
+    "318": "marina",
+    "319": "towel",
+    "320": "curtain",
+    "321": "apartment",
+    "322": "sinks",
+    "323": "graffiti",
+    "324": "shelves",
+    "325": "mask",
+    "326": "outside",
+    "327": "bar",
+    "328": "backyard",
+    "329": "rack",
+    "330": "urinal",
+    "331": "cap",
+    "332": "freight",
+    "333": "cupcake",
+    "334": "scooters",
+    "335": "paw",
+    "336": "ingredients",
+    "337": "bottles",
+    "338": "signs",
+    "339": "doorway",
+    "340": "library",
+    "341": "guitar",
+    "342": "slices",
+    "343": "crib",
+    "344": "barn",
+    "345": "chicken",
+    "346": "driveway",
+    "347": "cabinets",
+    "348": "drawer",
+    "349": "cupcakes",
+    "350": "apron",
+    "351": "bucket",
+    "352": "bats",
+    "353": "helmets",
+    "354": "shuttle",
+    "355": "kitty",
+    "356": "brick",
+    "357": "sofa",
+    "358": "pony",
+    "359": "frame",
+    "360": "pigeon",
+    "361": "pots",
+    "362": "coat",
+    "363": "trailer",
+    "364": "hallway",
+    "365": "can",
+    "366": "purse",
+    "367": "dryer",
+    "368": "outdoors",
+    "369": "tent",
+    "370": "hangar",
+    "371": "panda",
+    "372": "foil",
+    "373": "holder",
+    "374": "walls",
+    "375": "doors",
+    "376": "crosswalk",
+    "377": "trunks",
+    "378": "wheel",
+    "379": "colors",
+    "380": "tools",
+    "381": "coffee",
+    "382": "candle",
+    "383": "eagle",
+    "384": "beverage",
+    "385": "grizzly",
+    "386": "television",
+    "387": "tram",
+    "388": "pipe",
+    "389": "walkway",
+    "390": "bank",
+    "391": "side",
+    "392": "cigarette",
+    "393": "paddle",
+    "394": "taxi",
+    "395": "stick",
+    "396": "ram",
+    "397": "statues",
+    "398": "terminal",
+    "399": "pug",
+    "400": "shorts",
+    "401": "skies",
+    "402": "wheelchair",
+    "403": "vegetable",
+    "404": "flags",
+    "405": "baskets",
+    "406": "highway",
+    "407": "fireplace",
+    "408": "bun",
+    "409": "biplane",
+    "410": "warehouse",
+    "411": "dock",
+    "412": "classroom",
+    "413": "hamburger",
+    "414": "freezer",
+    "415": "cups",
+    "416": "roses",
+    "417": "refrigerators",
+    "418": "trail",
+    "419": "lane",
+    "420": "frisbees",
+    "421": "milk",
+    "422": "pans",
+    "423": "surface",
+    "424": "suits",
+    "425": "snowboards",
+    "426": "lake",
+    "427": "booth",
+    "428": "turkey",
+    "429": "canoe"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "airliner": 123,
+    "airplane": 12,
+    "airplanes": 70,
+    "airport": 176,
+    "apartment": 321,
+    "apple": 145,
+    "apples": 174,
+    "appliances": 311,
+    "apron": 350,
+    "backpack": 224,
+    "backyard": 328,
+    "bag": 124,
+    "bags": 217,
+    "ball": 42,
+    "banana": 91,
+    "bananas": 101,
+    "bank": 390,
+    "bar": 327,
+    "barn": 344,
+    "basket": 142,
+    "baskets": 405,
+    "bat": 48,
+    "bath": 158,
+    "bathroom": 25,
+    "bathtub": 275,
+    "bats": 352,
+    "beach": 107,
+    "bear": 17,
+    "bears": 65,
+    "bed": 41,
+    "bedroom": 99,
+    "beds": 160,
+    "beer": 302,
+    "bench": 60,
+    "benches": 148,
+    "beverage": 384,
+    "bicycle": 31,
+    "bicycles": 87,
+    "biplane": 409,
+    "bird": 23,
+    "birds": 63,
+    "black": 5,
+    "blender": 165,
+    "blue": 3,
+    "boards": 139,
+    "boat": 37,
+    "boats": 61,
+    "booth": 427,
+    "bottle": 149,
+    "bottles": 337,
+    "bowl": 51,
+    "box": 76,
+    "boxes": 249,
+    "bread": 228,
+    "breakfast": 259,
+    "brick": 356,
+    "bridge": 236,
+    "broccoli": 232,
+    "brown": 7,
+    "bucket": 351,
+    "building": 79,
+    "buildings": 221,
+    "bull": 205,
+    "bun": 408,
+    "bus": 11,
+    "buses": 58,
+    "cabinet": 246,
+    "cabinets": 347,
+    "cage": 247,
+    "cake": 34,
+    "cakes": 230,
+    "calf": 309,
+    "camera": 172,
+    "can": 365,
+    "candle": 382,
+    "candles": 231,
+    "canoe": 429,
+    "cap": 331,
+    "car": 33,
+    "cargo": 304,
+    "carriage": 112,
+    "carrot": 258,
+    "carrots": 206,
+    "cars": 54,
+    "cart": 117,
+    "case": 273,
+    "cat": 8,
+    "cats": 57,
+    "cattle": 175,
+    "cellphone": 126,
+    "chair": 75,
+    "chairs": 156,
+    "cheese": 292,
+    "chicken": 345,
+    "chocolate": 222,
+    "cigarette": 392,
+    "classroom": 412,
+    "clock": 32,
+    "clocks": 203,
+    "clothes": 314,
+    "coat": 362,
+    "coffee": 381,
+    "colors": 379,
+    "computer": 59,
+    "computers": 136,
+    "container": 131,
+    "containers": 268,
+    "couch": 166,
+    "counter": 137,
+    "cow": 50,
+    "cows": 52,
+    "crib": 343,
+    "crosswalk": 376,
+    "cup": 150,
+    "cupcake": 333,
+    "cupcakes": 349,
+    "cups": 415,
+    "curtain": 320,
+    "desk": 89,
+    "dessert": 213,
+    "device": 207,
+    "dinner": 208,
+    "dish": 121,
+    "dishes": 266,
+    "dock": 411,
+    "dog": 10,
+    "dogs": 68,
+    "donut": 77,
+    "donuts": 85,
+    "door": 113,
+    "doors": 375,
+    "doorway": 339,
+    "drawer": 348,
+    "dress": 281,
+    "drink": 235,
+    "drinks": 301,
+    "driveway": 346,
+    "dryer": 367,
+    "duck": 212,
+    "ducks": 219,
+    "eagle": 383,
+    "eight": 272,
+    "elephant": 21,
+    "elephants": 47,
+    "engine": 103,
+    "entree": 305,
+    "equipment": 216,
+    "fence": 229,
+    "fireplace": 407,
+    "fish": 300,
+    "five": 55,
+    "flag": 285,
+    "flags": 404,
+    "floor": 227,
+    "flower": 159,
+    "flowers": 92,
+    "foil": 372,
+    "fork": 198,
+    "four": 15,
+    "frame": 359,
+    "freezer": 414,
+    "freight": 332,
+    "fridge": 181,
+    "frisbee": 69,
+    "frisbees": 420,
+    "fruit": 119,
+    "fruits": 211,
+    "furniture": 276,
+    "garage": 226,
+    "garden": 274,
+    "gear": 284,
+    "giraffe": 20,
+    "giraffes": 26,
+    "glass": 280,
+    "glasses": 120,
+    "glove": 214,
+    "goat": 242,
+    "goats": 199,
+    "graffiti": 323,
+    "grass": 96,
+    "gray": 18,
+    "green": 4,
+    "grizzly": 385,
+    "guitar": 341,
+    "hallway": 364,
+    "hamburger": 413,
+    "hangar": 370,
+    "hat": 94,
+    "hats": 288,
+    "hay": 282,
+    "helicopter": 279,
+    "helmet": 147,
+    "helmets": 353,
+    "highway": 406,
+    "hill": 98,
+    "hillside": 189,
+    "holder": 373,
+    "horse": 27,
+    "horses": 39,
+    "hose": 299,
+    "house": 125,
+    "hydrant": 40,
+    "ingredients": 336,
+    "jacket": 220,
+    "jar": 306,
+    "jet": 62,
+    "jets": 133,
+    "keyboard": 177,
+    "kitchen": 24,
+    "kite": 45,
+    "kites": 67,
+    "kitten": 105,
+    "kitty": 355,
+    "knife": 140,
+    "lake": 426,
+    "lamb": 250,
+    "lambs": 286,
+    "lamp": 237,
+    "lane": 419,
+    "laptop": 71,
+    "laptops": 161,
+    "leaves": 245,
+    "library": 340,
+    "locomotive": 193,
+    "luggage": 143,
+    "lunch": 248,
+    "machine": 200,
+    "marina": 318,
+    "mask": 325,
+    "meal": 84,
+    "meat": 252,
+    "milk": 421,
+    "mirror": 74,
+    "monkey": 289,
+    "motorcycle": 28,
+    "motorcycles": 72,
+    "mountain": 109,
+    "mountains": 260,
+    "mouse": 190,
+    "museum": 313,
+    "nine": 294,
+    "ocean": 315,
+    "office": 151,
+    "one": 35,
+    "orange": 16,
+    "oranges": 173,
+    "outdoors": 368,
+    "outside": 326,
+    "oven": 90,
+    "owl": 293,
+    "paddle": 393,
+    "painting": 267,
+    "pan": 132,
+    "panda": 371,
+    "pans": 422,
+    "parrot": 210,
+    "pastries": 312,
+    "pastry": 265,
+    "paw": 335,
+    "pen": 135,
+    "phone": 53,
+    "phones": 146,
+    "photograph": 225,
+    "picture": 80,
+    "pictures": 254,
+    "pie": 257,
+    "pigeon": 360,
+    "pin": 253,
+    "pipe": 388,
+    "pizza": 22,
+    "pizzas": 110,
+    "plant": 144,
+    "plants": 277,
+    "plate": 29,
+    "plates": 169,
+    "platter": 303,
+    "pole": 186,
+    "poles": 239,
+    "pony": 358,
+    "pool": 233,
+    "pot": 194,
+    "pots": 361,
+    "pug": 399,
+    "puppy": 154,
+    "purple": 36,
+    "purse": 366,
+    "rack": 329,
+    "racquet": 141,
+    "rail": 191,
+    "ram": 396,
+    "ramp": 202,
+    "red": 2,
+    "refrigerator": 81,
+    "refrigerators": 417,
+    "remote": 264,
+    "remotes": 283,
+    "restaurant": 130,
+    "restroom": 195,
+    "river": 196,
+    "road": 78,
+    "room": 14,
+    "roses": 416,
+    "sailboat": 316,
+    "sailboats": 298,
+    "salad": 204,
+    "sandwich": 44,
+    "sandwiches": 155,
+    "scene": 243,
+    "scissors": 171,
+    "scooter": 170,
+    "scooters": 334,
+    "screen": 238,
+    "sculpture": 262,
+    "seagull": 215,
+    "seagulls": 290,
+    "seat": 295,
+    "seven": 162,
+    "sheep": 46,
+    "shelf": 209,
+    "shelves": 324,
+    "ship": 223,
+    "shirt": 115,
+    "shop": 178,
+    "shorts": 400,
+    "shower": 197,
+    "shuttle": 354,
+    "side": 391,
+    "sidewalk": 183,
+    "sign": 134,
+    "signs": 338,
+    "sink": 82,
+    "sinks": 322,
+    "six": 102,
+    "skateboard": 73,
+    "skateboards": 244,
+    "ski": 187,
+    "skies": 401,
+    "skis": 64,
+    "sky": 168,
+    "slice": 310,
+    "slices": 342,
+    "snack": 308,
+    "snowboard": 97,
+    "snowboards": 425,
+    "sofa": 357,
+    "spoon": 278,
+    "stadium": 296,
+    "stall": 241,
+    "station": 111,
+    "statue": 164,
+    "statues": 397,
+    "stick": 395,
+    "store": 129,
+    "stove": 163,
+    "street": 106,
+    "subway": 269,
+    "suit": 182,
+    "suitcase": 93,
+    "suitcases": 138,
+    "suits": 424,
+    "sun": 157,
+    "sunglasses": 271,
+    "surface": 423,
+    "surfboard": 86,
+    "surfboards": 152,
+    "table": 179,
+    "tablet": 317,
+    "taxi": 394,
+    "television": 386,
+    "ten": 291,
+    "tent": 369,
+    "terminal": 398,
+    "three": 6,
+    "tie": 88,
+    "ties": 263,
+    "toilet": 56,
+    "toilets": 218,
+    "tools": 380,
+    "toothbrush": 167,
+    "toothbrushes": 261,
+    "towel": 319,
+    "towels": 255,
+    "tower": 66,
+    "toy": 127,
+    "toys": 287,
+    "track": 270,
+    "tracks": 192,
+    "trail": 418,
+    "trailer": 363,
+    "train": 13,
+    "trains": 95,
+    "tram": 387,
+    "tray": 116,
+    "tree": 108,
+    "trees": 185,
+    "trolley": 297,
+    "truck": 19,
+    "trucks": 104,
+    "trunk": 188,
+    "trunks": 377,
+    "tub": 234,
+    "turkey": 428,
+    "tv": 256,
+    "two": 0,
+    "umbrella": 49,
+    "umbrellas": 100,
+    "uniform": 307,
+    "urinal": 330,
+    "urinals": 251,
+    "vase": 43,
+    "vases": 122,
+    "vegetable": 403,
+    "vegetables": 114,
+    "vehicle": 128,
+    "vehicles": 184,
+    "vest": 201,
+    "wagon": 240,
+    "walkway": 389,
+    "wall": 118,
+    "walls": 374,
+    "warehouse": 410,
+    "wheel": 378,
+    "wheelchair": 402,
+    "white": 1,
+    "window": 83,
+    "wine": 153,
+    "yellow": 9,
+    "zebra": 30,
+    "zebras": 38,
+    "zoo": 180
+  },
+  "layer_norm_eps": 1e-12,
+  "max_image_length": -1,
+  "max_position_embeddings": 40,
+  "modality_type_vocab_size": 2,
+  "model_type": "vilt",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "num_images": -1,
+  "patch_size": 32,
+  "qkv_bias": true,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb14b2b8341f4b18df96f4624e989d852eabf58d12d737e18444275c9954c0b
+size 453785512