Upload VJEPA2ForVideoClassification

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 +1,482 @@
+{
+  "architectures": [
+    "VJEPA2ForVideoClassification"
+  ],
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.0,
+  "crop_size": 256,
+  "drop_path_rate": 0.0,
+  "frames_per_clip": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "ApplyLipstick",
+    "1": "ApplyEyeMakeup",
+    "2": "Biking",
+    "3": "BrushingTeeth",
+    "4": "CuttingInKitchen",
+    "5": "Haircut",
+    "6": "HandstandWalking",
+    "7": "HandstandPushups",
+    "8": "Hammering",
+    "9": "Knitting",
+    "10": "Typing",
+    "11": "BlowDryHair",
+    "12": "PlayingDaf",
+    "13": "HeadMassage",
+    "14": "WalkingWithDog",
+    "15": "Sitting",
+    "16": "Standing",
+    "17": "Walking",
+    "18": "DrinkAngry",
+    "19": "DrinkDisgust",
+    "20": "DrinkHappy",
+    "21": "DrinkNeutral",
+    "22": "DrinkSad",
+    "23": "PutonglassesAngry",
+    "24": "PutonglassesHappy",
+    "25": "PutonglassesNeutral",
+    "26": "PutonglassesSad",
+    "27": "PutonjacketAngry",
+    "28": "PutonjacketHappy",
+    "29": "PutonjacketNeutral",
+    "30": "PutonjacketSad",
+    "31": "ReadAngry",
+    "32": "ReadHappy",
+    "33": "ReadNeutral",
+    "34": "ReadSad",
+    "35": "SitdownAngry",
+    "36": "SitdownHappy",
+    "37": "SitdownNeutral",
+    "38": "SitdownSad",
+    "39": "StandupAngry",
+    "40": "StandupHappy",
+    "41": "StandupNeutral",
+    "42": "StandupSad",
+    "43": "TakeoffglassesAngry",
+    "44": "TakeoffglassesHappy",
+    "45": "TakeoffglassesNeutral",
+    "46": "TakeoffglassesSad",
+    "47": "TakeoffjacketAngry",
+    "48": "TakeoffjacketHappy",
+    "49": "TakeoffjacketNeutral",
+    "50": "TakeoffjacketSad",
+    "51": "WriteAngry",
+    "52": "WriteHappy",
+    "53": "WriteNeutral",
+    "54": "ViolenceFighting",
+    "55": "Fighting",
+    "56": "Waving",
+    "57": "Clapping",
+    "58": "WalkingWhileUsingPhone",
+    "59": "Jump",
+    "60": "SitDown",
+    "61": "LyingDown",
+    "62": "StandUp",
+    "63": "FallDown",
+    "64": "ClosingABook",
+    "65": "ClosingABox",
+    "66": "ClosingAClosetCabinet",
+    "67": "ClosingADoor",
+    "68": "ClosingALaptop",
+    "69": "ClosingARefrigerator",
+    "70": "ClosingAWindow",
+    "71": "DrinkingFromACupGlassBottle",
+    "72": "EatingASandwich",
+    "73": "FixingADoor",
+    "74": "FixingADoorknob",
+    "75": "FixingALight",
+    "76": "FixingAVacuum",
+    "77": "FixingTheirHair",
+    "78": "GraspingOntoADoorknob",
+    "79": "HoldingABag",
+    "80": "HoldingABlanket",
+    "81": "HoldingABook",
+    "82": "HoldingABox",
+    "83": "HoldingABroom",
+    "84": "HoldingACupGlassBottleOfSomething",
+    "85": "HoldingADish",
+    "86": "HoldingALaptop",
+    "87": "HoldingAMirror",
+    "88": "HoldingAPhoneCamera",
+    "89": "HoldingAPicture",
+    "90": "HoldingAPillow",
+    "91": "HoldingASandwich",
+    "92": "HoldingAShoeShoes",
+    "93": "HoldingATowelS",
+    "94": "HoldingAVacuum",
+    "95": "HoldingSomeClothes",
+    "96": "HoldingSomeFood",
+    "97": "HoldingSomeMedicine",
+    "98": "LaughingAtAPicture",
+    "99": "LaughingAtTelevision",
+    "100": "LyingOnABed",
+    "101": "LyingOnASofaCouch",
+    "102": "LyingOnTheFloor",
+    "103": "MakingASandwich",
+    "104": "OpeningABag",
+    "105": "OpeningABook",
+    "106": "OpeningABox",
+    "107": "OpeningAClosetCabinet",
+    "108": "OpeningADoor",
+    "109": "OpeningALaptop",
+    "110": "OpeningARefrigerator",
+    "111": "OpeningAWindow",
+    "112": "PlayingWithAPhoneCamera",
+    "113": "PouringSomethingIntoACupGlassBottle",
+    "114": "PuttingABagSomewhere",
+    "115": "PuttingABlanketSomewhere",
+    "116": "PuttingABookSomewhere",
+    "117": "PuttingABoxSomewhere",
+    "118": "PuttingABroomSomewhere",
+    "119": "PuttingACupGlassBottleSomewhere",
+    "120": "PuttingADishEsSomewhere",
+    "121": "PuttingALaptopSomewhere",
+    "122": "PuttingAPhoneCameraSomewhere",
+    "123": "PuttingAPictureSomewhere",
+    "124": "PuttingAPillowSomewhere",
+    "125": "PuttingASandwichSomewhere",
+    "126": "PuttingATowelSSomewhere",
+    "127": "PuttingClothesSomewhere",
+    "128": "PuttingGroceriesSomewhere",
+    "129": "PuttingOnShoeShoes",
+    "130": "PuttingShoesSomewhere",
+    "131": "PuttingSomeFoodSomewhere",
+    "132": "PuttingSomethingOnAShelf",
+    "133": "PuttingSomethingOnATable",
+    "134": "PuttingTheirPaperNotebookSomewhere",
+    "135": "ReachingForAndGrabbingAPicture",
+    "136": "SittingAtATable",
+    "137": "SittingInABed",
+    "138": "SittingInAChair",
+    "139": "SittingOnATable",
+    "140": "SittingOnSofaCouch",
+    "141": "SittingOnTheFloor",
+    "142": "SmilingAtABook",
+    "143": "SmilingInAMirror",
+    "144": "SnugglingWithABlanket",
+    "145": "SnugglingWithAPillow",
+    "146": "SomeoneIsAwakeningInBed",
+    "147": "SomeoneIsAwakeningSomewhere",
+    "148": "SomeoneIsCookingSomething",
+    "149": "SomeoneIsDressing",
+    "150": "SomeoneIsEatingSomething",
+    "151": "SomeoneIsGoingFromStandingToSitting",
+    "152": "SomeoneIsHoldingAPaperNotebook",
+    "153": "SomeoneIsLaughing",
+    "154": "SomeoneIsRunningSomewhere",
+    "155": "SomeoneIsSmiling",
+    "156": "SomeoneIsSneezing",
+    "157": "SomeoneIsStandingUpFromSomewhere",
+    "158": "SomeoneIsUndressing",
+    "159": "StandingOnAChair",
+    "160": "TakingABagFromSomewhere",
+    "161": "TakingABlanketFromSomewhere",
+    "162": "TakingABookFromSomewhere",
+    "163": "TakingABoxFromSomewhere",
+    "164": "TakingABroomFromSomewhere",
+    "165": "TakingACupGlassBottleFromSomewhere",
+    "166": "TakingADishEsFromSomewhere",
+    "167": "TakingALaptopFromSomewhere",
+    "168": "TakingAPhoneCameraFromSomewhere",
+    "169": "TakingAPictureOfSomething",
+    "170": "TakingAPillowFromSomewhere",
+    "171": "TakingASandwichFromSomewhere",
+    "172": "TakingATowelSFromSomewhere",
+    "173": "TakingAVacuumFromSomewhere",
+    "174": "TakingConsumingSomeMedicine",
+    "175": "TakingFoodFromSomewhere",
+    "176": "TakingOffSomeShoes",
+    "177": "TakingPaperNotebookFromSomewhere",
+    "178": "TakingShoesFromSomewhere",
+    "179": "TakingSomeClothesFromSomewhere",
+    "180": "TakingSomethingFromABox",
+    "181": "TalkingOnAPhoneCamera",
+    "182": "ThrowingABagSomewhere",
+    "183": "ThrowingABlanketSomewhere",
+    "184": "ThrowingABookSomewhere",
+    "185": "ThrowingABoxSomewhere",
+    "186": "ThrowingABroomSomewhere",
+    "187": "ThrowingAPillowSomewhere",
+    "188": "ThrowingATowelSSomewhere",
+    "189": "ThrowingClothesSomewhere",
+    "190": "ThrowingFoodSomewhere",
+    "191": "ThrowingShoesSomewhere",
+    "192": "ThrowingSomethingOnTheFloor",
+    "193": "TidyingAShelfOrSomethingOnAShelf",
+    "194": "TidyingSomeClothes",
+    "195": "TidyingSomethingOnTheFloor",
+    "196": "TidyingUpABlanketS",
+    "197": "TidyingUpAClosetCabinet",
+    "198": "TidyingUpATable",
+    "199": "TidyingUpATowelS",
+    "200": "TidyingUpWithABroom",
+    "201": "TurningOffALight",
+    "202": "TurningOnALight",
+    "203": "WalkingThroughADoorway",
+    "204": "WashADishDishes",
+    "205": "WashingACupGlassBottle",
+    "206": "WashingAMirror",
+    "207": "WashingATable",
+    "208": "WashingAWindow",
+    "209": "WashingSomeClothes",
+    "210": "WashingSomethingWithATowel",
+    "211": "WashingTheirHands",
+    "212": "WatchingALaptopOrSomethingOnALaptop",
+    "213": "WatchingLookingAtAPicture",
+    "214": "WatchingLookingOutsideOfAWindow",
+    "215": "WatchingReadingLookingAtABook",
+    "216": "WatchingSomethingSomeoneThemselvesInAMirror",
+    "217": "WatchingTelevision",
+    "218": "WorkingAtATable",
+    "219": "WorkingOnPaperNotebook",
+    "220": "WorkingPlayingOnALaptop"
+  },
+  "image_size": 256,
+  "in_chans": 3,
+  "initializer_range": 0.02,
+  "label2id": {
+    "ApplyEyeMakeup": 1,
+    "ApplyLipstick": 0,
+    "Biking": 2,
+    "BlowDryHair": 11,
+    "BrushingTeeth": 3,
+    "Clapping": 57,
+    "ClosingABook": 64,
+    "ClosingABox": 65,
+    "ClosingAClosetCabinet": 66,
+    "ClosingADoor": 67,
+    "ClosingALaptop": 68,
+    "ClosingARefrigerator": 69,
+    "ClosingAWindow": 70,
+    "CuttingInKitchen": 4,
+    "DrinkAngry": 18,
+    "DrinkDisgust": 19,
+    "DrinkHappy": 20,
+    "DrinkNeutral": 21,
+    "DrinkSad": 22,
+    "DrinkingFromACupGlassBottle": 71,
+    "EatingASandwich": 72,
+    "FallDown": 63,
+    "Fighting": 55,
+    "FixingADoor": 73,
+    "FixingADoorknob": 74,
+    "FixingALight": 75,
+    "FixingAVacuum": 76,
+    "FixingTheirHair": 77,
+    "GraspingOntoADoorknob": 78,
+    "Haircut": 5,
+    "Hammering": 8,
+    "HandstandPushups": 7,
+    "HandstandWalking": 6,
+    "HeadMassage": 13,
+    "HoldingABag": 79,
+    "HoldingABlanket": 80,
+    "HoldingABook": 81,
+    "HoldingABox": 82,
+    "HoldingABroom": 83,
+    "HoldingACupGlassBottleOfSomething": 84,
+    "HoldingADish": 85,
+    "HoldingALaptop": 86,
+    "HoldingAMirror": 87,
+    "HoldingAPhoneCamera": 88,
+    "HoldingAPicture": 89,
+    "HoldingAPillow": 90,
+    "HoldingASandwich": 91,
+    "HoldingAShoeShoes": 92,
+    "HoldingATowelS": 93,
+    "HoldingAVacuum": 94,
+    "HoldingSomeClothes": 95,
+    "HoldingSomeFood": 96,
+    "HoldingSomeMedicine": 97,
+    "Jump": 59,
+    "Knitting": 9,
+    "LaughingAtAPicture": 98,
+    "LaughingAtTelevision": 99,
+    "LyingDown": 61,
+    "LyingOnABed": 100,
+    "LyingOnASofaCouch": 101,
+    "LyingOnTheFloor": 102,
+    "MakingASandwich": 103,
+    "OpeningABag": 104,
+    "OpeningABook": 105,
+    "OpeningABox": 106,
+    "OpeningAClosetCabinet": 107,
+    "OpeningADoor": 108,
+    "OpeningALaptop": 109,
+    "OpeningARefrigerator": 110,
+    "OpeningAWindow": 111,
+    "PlayingDaf": 12,
+    "PlayingWithAPhoneCamera": 112,
+    "PouringSomethingIntoACupGlassBottle": 113,
+    "PutonglassesAngry": 23,
+    "PutonglassesHappy": 24,
+    "PutonglassesNeutral": 25,
+    "PutonglassesSad": 26,
+    "PutonjacketAngry": 27,
+    "PutonjacketHappy": 28,
+    "PutonjacketNeutral": 29,
+    "PutonjacketSad": 30,
+    "PuttingABagSomewhere": 114,
+    "PuttingABlanketSomewhere": 115,
+    "PuttingABookSomewhere": 116,
+    "PuttingABoxSomewhere": 117,
+    "PuttingABroomSomewhere": 118,
+    "PuttingACupGlassBottleSomewhere": 119,
+    "PuttingADishEsSomewhere": 120,
+    "PuttingALaptopSomewhere": 121,
+    "PuttingAPhoneCameraSomewhere": 122,
+    "PuttingAPictureSomewhere": 123,
+    "PuttingAPillowSomewhere": 124,
+    "PuttingASandwichSomewhere": 125,
+    "PuttingATowelSSomewhere": 126,
+    "PuttingClothesSomewhere": 127,
+    "PuttingGroceriesSomewhere": 128,
+    "PuttingOnShoeShoes": 129,
+    "PuttingShoesSomewhere": 130,
+    "PuttingSomeFoodSomewhere": 131,
+    "PuttingSomethingOnAShelf": 132,
+    "PuttingSomethingOnATable": 133,
+    "PuttingTheirPaperNotebookSomewhere": 134,
+    "ReachingForAndGrabbingAPicture": 135,
+    "ReadAngry": 31,
+    "ReadHappy": 32,
+    "ReadNeutral": 33,
+    "ReadSad": 34,
+    "SitDown": 60,
+    "SitdownAngry": 35,
+    "SitdownHappy": 36,
+    "SitdownNeutral": 37,
+    "SitdownSad": 38,
+    "Sitting": 15,
+    "SittingAtATable": 136,
+    "SittingInABed": 137,
+    "SittingInAChair": 138,
+    "SittingOnATable": 139,
+    "SittingOnSofaCouch": 140,
+    "SittingOnTheFloor": 141,
+    "SmilingAtABook": 142,
+    "SmilingInAMirror": 143,
+    "SnugglingWithABlanket": 144,
+    "SnugglingWithAPillow": 145,
+    "SomeoneIsAwakeningInBed": 146,
+    "SomeoneIsAwakeningSomewhere": 147,
+    "SomeoneIsCookingSomething": 148,
+    "SomeoneIsDressing": 149,
+    "SomeoneIsEatingSomething": 150,
+    "SomeoneIsGoingFromStandingToSitting": 151,
+    "SomeoneIsHoldingAPaperNotebook": 152,
+    "SomeoneIsLaughing": 153,
+    "SomeoneIsRunningSomewhere": 154,
+    "SomeoneIsSmiling": 155,
+    "SomeoneIsSneezing": 156,
+    "SomeoneIsStandingUpFromSomewhere": 157,
+    "SomeoneIsUndressing": 158,
+    "StandUp": 62,
+    "Standing": 16,
+    "StandingOnAChair": 159,
+    "StandupAngry": 39,
+    "StandupHappy": 40,
+    "StandupNeutral": 41,
+    "StandupSad": 42,
+    "TakeoffglassesAngry": 43,
+    "TakeoffglassesHappy": 44,
+    "TakeoffglassesNeutral": 45,
+    "TakeoffglassesSad": 46,
+    "TakeoffjacketAngry": 47,
+    "TakeoffjacketHappy": 48,
+    "TakeoffjacketNeutral": 49,
+    "TakeoffjacketSad": 50,
+    "TakingABagFromSomewhere": 160,
+    "TakingABlanketFromSomewhere": 161,
+    "TakingABookFromSomewhere": 162,
+    "TakingABoxFromSomewhere": 163,
+    "TakingABroomFromSomewhere": 164,
+    "TakingACupGlassBottleFromSomewhere": 165,
+    "TakingADishEsFromSomewhere": 166,
+    "TakingALaptopFromSomewhere": 167,
+    "TakingAPhoneCameraFromSomewhere": 168,
+    "TakingAPictureOfSomething": 169,
+    "TakingAPillowFromSomewhere": 170,
+    "TakingASandwichFromSomewhere": 171,
+    "TakingATowelSFromSomewhere": 172,
+    "TakingAVacuumFromSomewhere": 173,
+    "TakingConsumingSomeMedicine": 174,
+    "TakingFoodFromSomewhere": 175,
+    "TakingOffSomeShoes": 176,
+    "TakingPaperNotebookFromSomewhere": 177,
+    "TakingShoesFromSomewhere": 178,
+    "TakingSomeClothesFromSomewhere": 179,
+    "TakingSomethingFromABox": 180,
+    "TalkingOnAPhoneCamera": 181,
+    "ThrowingABagSomewhere": 182,
+    "ThrowingABlanketSomewhere": 183,
+    "ThrowingABookSomewhere": 184,
+    "ThrowingABoxSomewhere": 185,
+    "ThrowingABroomSomewhere": 186,
+    "ThrowingAPillowSomewhere": 187,
+    "ThrowingATowelSSomewhere": 188,
+    "ThrowingClothesSomewhere": 189,
+    "ThrowingFoodSomewhere": 190,
+    "ThrowingShoesSomewhere": 191,
+    "ThrowingSomethingOnTheFloor": 192,
+    "TidyingAShelfOrSomethingOnAShelf": 193,
+    "TidyingSomeClothes": 194,
+    "TidyingSomethingOnTheFloor": 195,
+    "TidyingUpABlanketS": 196,
+    "TidyingUpAClosetCabinet": 197,
+    "TidyingUpATable": 198,
+    "TidyingUpATowelS": 199,
+    "TidyingUpWithABroom": 200,
+    "TurningOffALight": 201,
+    "TurningOnALight": 202,
+    "Typing": 10,
+    "ViolenceFighting": 54,
+    "Walking": 17,
+    "WalkingThroughADoorway": 203,
+    "WalkingWhileUsingPhone": 58,
+    "WalkingWithDog": 14,
+    "WashADishDishes": 204,
+    "WashingACupGlassBottle": 205,
+    "WashingAMirror": 206,
+    "WashingATable": 207,
+    "WashingAWindow": 208,
+    "WashingSomeClothes": 209,
+    "WashingSomethingWithATowel": 210,
+    "WashingTheirHands": 211,
+    "WatchingALaptopOrSomethingOnALaptop": 212,
+    "WatchingLookingAtAPicture": 213,
+    "WatchingLookingOutsideOfAWindow": 214,
+    "WatchingReadingLookingAtABook": 215,
+    "WatchingSomethingSomeoneThemselvesInAMirror": 216,
+    "WatchingTelevision": 217,
+    "Waving": 56,
+    "WorkingAtATable": 218,
+    "WorkingOnPaperNotebook": 219,
+    "WorkingPlayingOnALaptop": 220,
+    "WriteAngry": 51,
+    "WriteHappy": 52,
+    "WriteNeutral": 53
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratio": 4,
+  "model_type": "vjepa2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_pooler_layers": 3,
+  "patch_size": 16,
+  "pred_hidden_size": 384,
+  "pred_mlp_ratio": 4.0,
+  "pred_num_attention_heads": 12,
+  "pred_num_hidden_layers": 12,
+  "pred_num_mask_tokens": 10,
+  "pred_zero_init_mask_tokens": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.0.dev0",
+  "tubelet_size": 2,
+  "use_SiLU": false,
+  "wide_SiLU": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41b352c60ce669799e3b6d9d604ddb815dedf1a2a258f91fc2fe490605e385e
+size 1502211292