Duplicate from facebook/vjepa2-vitg-fpc64-384-ssv2

Co-authored-by: Meta Platforms <meta-bot@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,94 @@
+---
+license: mit
+pipeline_tag: video-classification
+tags:
+- video
+library_name: transformers
+datasets:
+- HuggingFaceM4/something_something_v2
+base_model:
+- facebook/vjepa2-vitg-fpc64-384
+---
+
+# V-JEPA 2
+
+A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of [VJEPA](https://ai.meta.com/blog/v-jepa-yann-lecun-ai-model-video-joint-embedding-predictive-architecture/), resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale.
+The code is released [in this repository](https://github.com/facebookresearch/vjepa2).
+
+<div style="background-color: rgba(251, 255, 120, 0.4); padding: 10px; color: black; border-radius: 5px; box-shadow: 0 4px 8px rgba(0,0,0,0.1);">
+    💡 This is V-JEPA 2 <a href="https://huggingface.co/facebook/vjepa2-vitg-fpc64-384">ViT-g 384</a> model with video classification head pretrained on <a href="https://paperswithcode.com/dataset/something-something-v2" style="color: black;">Something-Something-V2</a> dataset.
+</div>
+<br></br>
+
+<img src="https://github.com/user-attachments/assets/914942d8-6a1e-409d-86ff-ff856b7346ab">&nbsp;
+
+## Installation
+
+To run V-JEPA 2 model, ensure you have installed the latest transformers:
+
+```bash
+pip install -U git+https://github.com/huggingface/transformers
+```
+
+## Video classification code snippet
+
+```python
+import torch
+import numpy as np
+
+from torchcodec.decoders import VideoDecoder
+from transformers import AutoVideoProcessor, AutoModelForVideoClassification
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load model and video preprocessor
+hf_repo = "facebook/vjepa2-vitg-fpc64-384-ssv2"
+
+model = AutoModelForVideoClassification.from_pretrained(hf_repo).to(device)
+processor = AutoVideoProcessor.from_pretrained(hf_repo)
+
+# To load a video, sample the number of frames according to the model.
+# For this model, we use 64.
+video_url = "https://huggingface.co/datasets/nateraw/kinetics-mini/resolve/main/val/bowling/-WH-lxmGJVY_000005_000015.mp4"
+vr = VideoDecoder(video_url)
+frame_idx = np.arange(0, model.config.frames_per_clip, 2) # you can define more complex sampling strategy
+video = vr.get_frames_at(indices=frame_idx).data  # frames x channels x height x width
+
+# Preprocess and run inference
+inputs = processor(video, return_tensors="pt").to(model.device)
+with torch.no_grad():
+    outputs = model(**inputs)
+logits = outputs.logits
+
+print("Top 5 predicted class names:")
+top5_indices = logits.topk(5).indices[0]
+top5_probs = torch.softmax(logits, dim=-1).topk(5).values[0]
+for idx, prob in zip(top5_indices, top5_probs):
+    text_label = model.config.id2label[idx.item()]
+    print(f" - {text_label}: {prob:.2f}")
+```
+Output:
+```
+Top 5 predicted class names:
+ - Putting [something] onto [something]: 0.39
+ - Putting [something similar to other things that are already on the table]: 0.23
+ - Stacking [number of] [something]: 0.07
+ - Putting [something] into [something]: 0.04
+ - Putting [number of] [something] onto [something]: 0.03
+```
+
+## Citation
+
+```
+@techreport{assran2025vjepa2,
+  title={V-JEPA~2: Self-Supervised Video Models Enable Understanding, Prediction and Planning},
+  author={Assran, Mahmoud and Bardes, Adrien and Fan, David and Garrido, Quentin and Howes, Russell and
+  Komeili, Mojtaba and Muckley, Matthew and Rizvi, Ammar and Roberts, Claire and Sinha, Koustuv and Zholus, Artem and
+  Arnaud, Sergio and Gejji, Abha and Martin, Ada and Robert Hogan, Francois and Dugas, Daniel and
+  Bojanowski, Piotr and Khalidov, Vasil and Labatut, Patrick and Massa, Francisco and Szafraniec, Marc and
+  Krishnakumar, Kapil and Li, Yong and Ma, Xiaodong and Chandar, Sarath and Meier, Franziska and LeCun, Yann and
+  Rabbat, Michael and Ballas, Nicolas},
+  institution={FAIR at Meta},
+  year={2025}
+}
+```

config.json

@@ -0,0 +1,386 @@
+{
+  "architectures": [
+    "VJEPA2ForVideoClassification"
+  ],
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.0,
+  "crop_size": 384,
+  "drop_path_rate": 0.0,
+  "frames_per_clip": 64,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1408,
+  "id2label": {
+    "0": "Approaching [something] with your camera",
+    "1": "Attaching [something] to [something]",
+    "2": "Bending [something] so that it deforms",
+    "3": "Bending [something] until it breaks",
+    "4": "Burying [something] in [something]",
+    "5": "Closing [something]",
+    "6": "Covering [something] with [something]",
+    "7": "Digging [something] out of [something]",
+    "8": "Dropping [something] behind [something]",
+    "9": "Dropping [something] in front of [something]",
+    "10": "Dropping [something] into [something]",
+    "11": "Dropping [something] next to [something]",
+    "12": "Dropping [something] onto [something]",
+    "13": "Failing to put [something] into [something] because [something] does not fit",
+    "14": "Folding [something]",
+    "15": "Hitting [something] with [something]",
+    "16": "Holding [something]",
+    "17": "Holding [something] behind [something]",
+    "18": "Holding [something] in front of [something]",
+    "19": "Holding [something] next to [something]",
+    "20": "Holding [something] over [something]",
+    "21": "Laying [something] on the table on its side, not upright",
+    "22": "Letting [something] roll along a flat surface",
+    "23": "Letting [something] roll down a slanted surface",
+    "24": "Letting [something] roll up a slanted surface, so it rolls back down",
+    "25": "Lifting a surface with [something] on it but not enough for it to slide down",
+    "26": "Lifting a surface with [something] on it until it starts sliding down",
+    "27": "Lifting [something] up completely without letting it drop down",
+    "28": "Lifting [something] up completely, then letting it drop down",
+    "29": "Lifting [something] with [something] on it",
+    "30": "Lifting up one end of [something] without letting it drop down",
+    "31": "Lifting up one end of [something], then letting it drop down",
+    "32": "Moving away from [something] with your camera",
+    "33": "Moving [part] of [something]",
+    "34": "Moving [something] across a surface until it falls down",
+    "35": "Moving [something] across a surface without it falling down",
+    "36": "Moving [something] and [something] away from each other",
+    "37": "Moving [something] and [something] closer to each other",
+    "38": "Moving [something] and [something] so they collide with each other",
+    "39": "Moving [something] and [something] so they pass each other",
+    "40": "Moving [something] away from [something]",
+    "41": "Moving [something] away from the camera",
+    "42": "Moving [something] closer to [something]",
+    "43": "Moving [something] down",
+    "44": "Moving [something] towards the camera",
+    "45": "Moving [something] up",
+    "46": "Opening [something]",
+    "47": "Picking [something] up",
+    "48": "Piling [something] up",
+    "49": "Plugging [something] into [something]",
+    "50": "Plugging [something] into [something] but pulling it right out as you remove your hand",
+    "51": "Poking a hole into [some substance]",
+    "52": "Poking a hole into [something soft]",
+    "53": "Poking a stack of [something] so the stack collapses",
+    "54": "Poking a stack of [something] without the stack collapsing",
+    "55": "Poking [something] so it slightly moves",
+    "56": "Poking [something] so lightly that it doesn't or almost doesn't move",
+    "57": "Poking [something] so that it falls over",
+    "58": "Poking [something] so that it spins around",
+    "59": "Pouring [something] into [something]",
+    "60": "Pouring [something] into [something] until it overflows",
+    "61": "Pouring [something] onto [something]",
+    "62": "Pouring [something] out of [something]",
+    "63": "Pretending or failing to wipe [something] off of [something]",
+    "64": "Pretending or trying and failing to twist [something]",
+    "65": "Pretending to be tearing [something that is not tearable]",
+    "66": "Pretending to close [something] without actually closing it",
+    "67": "Pretending to open [something] without actually opening it",
+    "68": "Pretending to pick [something] up",
+    "69": "Pretending to poke [something]",
+    "70": "Pretending to pour [something] out of [something], but [something] is empty",
+    "71": "Pretending to put [something] behind [something]",
+    "72": "Pretending to put [something] into [something]",
+    "73": "Pretending to put [something] next to [something]",
+    "74": "Pretending to put [something] on a surface",
+    "75": "Pretending to put [something] onto [something]",
+    "76": "Pretending to put [something] underneath [something]",
+    "77": "Pretending to scoop [something] up with [something]",
+    "78": "Pretending to spread air onto [something]",
+    "79": "Pretending to sprinkle air onto [something]",
+    "80": "Pretending to squeeze [something]",
+    "81": "Pretending to take [something] from [somewhere]",
+    "82": "Pretending to take [something] out of [something]",
+    "83": "Pretending to throw [something]",
+    "84": "Pretending to turn [something] upside down",
+    "85": "Pulling [something] from behind of [something]",
+    "86": "Pulling [something] from left to right",
+    "87": "Pulling [something] from right to left",
+    "88": "Pulling [something] onto [something]",
+    "89": "Pulling [something] out of [something]",
+    "90": "Pulling two ends of [something] but nothing happens",
+    "91": "Pulling two ends of [something] so that it gets stretched",
+    "92": "Pulling two ends of [something] so that it separates into two pieces",
+    "93": "Pushing [something] from left to right",
+    "94": "Pushing [something] from right to left",
+    "95": "Pushing [something] off of [something]",
+    "96": "Pushing [something] onto [something]",
+    "97": "Pushing [something] so it spins",
+    "98": "Pushing [something] so that it almost falls off but doesn't",
+    "99": "Pushing [something] so that it falls off the table",
+    "100": "Pushing [something] so that it slightly moves",
+    "101": "Pushing [something] with [something]",
+    "102": "Putting [number of] [something] onto [something]",
+    "103": "Putting [something] and [something] on the table",
+    "104": "Putting [something] behind [something]",
+    "105": "Putting [something] in front of [something]",
+    "106": "Putting [something] into [something]",
+    "107": "Putting [something] next to [something]",
+    "108": "Putting [something] on a flat surface without letting it roll",
+    "109": "Putting [something] on a surface",
+    "110": "Putting [something] on the edge of [something] so it is not supported and falls down",
+    "111": "Putting [something] onto a slanted surface but it doesn't glide down",
+    "112": "Putting [something] onto [something]",
+    "113": "Putting [something] onto [something else that cannot support it] so it falls down",
+    "114": "Putting [something similar to other things that are already on the table]",
+    "115": "Putting [something] that can't roll onto a slanted surface, so it slides down",
+    "116": "Putting [something] that can't roll onto a slanted surface, so it stays where it is",
+    "117": "Putting [something that cannot actually stand upright] upright on the table, so it falls on its side",
+    "118": "Putting [something] underneath [something]",
+    "119": "Putting [something] upright on the table",
+    "120": "Putting [something], [something] and [something] on the table",
+    "121": "Removing [something], revealing [something] behind",
+    "122": "Rolling [something] on a flat surface",
+    "123": "Scooping [something] up with [something]",
+    "124": "Showing a photo of [something] to the camera",
+    "125": "Showing [something] behind [something]",
+    "126": "Showing [something] next to [something]",
+    "127": "Showing [something] on top of [something]",
+    "128": "Showing [something] to the camera",
+    "129": "Showing that [something] is empty",
+    "130": "Showing that [something] is inside [something]",
+    "131": "[Something] being deflected from [something]",
+    "132": "[Something] colliding with [something] and both are being deflected",
+    "133": "[Something] colliding with [something] and both come to a halt",
+    "134": "[Something] falling like a feather or paper",
+    "135": "[Something] falling like a rock",
+    "136": "Spilling [something] behind [something]",
+    "137": "Spilling [something] next to [something]",
+    "138": "Spilling [something] onto [something]",
+    "139": "Spinning [something] so it continues spinning",
+    "140": "Spinning [something] that quickly stops spinning",
+    "141": "Spreading [something] onto [something]",
+    "142": "Sprinkling [something] onto [something]",
+    "143": "Squeezing [something]",
+    "144": "Stacking [number of] [something]",
+    "145": "Stuffing [something] into [something]",
+    "146": "Taking [one of many similar things on the table]",
+    "147": "Taking [something] from [somewhere]",
+    "148": "Taking [something] out of [something]",
+    "149": "Tearing [something] into two pieces",
+    "150": "Tearing [something] just a little bit",
+    "151": "Throwing [something]",
+    "152": "Throwing [something] against [something]",
+    "153": "Throwing [something] in the air and catching it",
+    "154": "Throwing [something] in the air and letting it fall",
+    "155": "Throwing [something] onto a surface",
+    "156": "Tilting [something] with [something] on it slightly so it doesn't fall down",
+    "157": "Tilting [something] with [something] on it until it falls off",
+    "158": "Tipping [something] over",
+    "159": "Tipping [something] with [something in it] over, so [something in it] falls out",
+    "160": "Touching (without moving) [part] of [something]",
+    "161": "Trying but failing to attach [something] to [something] because it doesn't stick",
+    "162": "Trying to bend [something unbendable] so nothing happens",
+    "163": "Trying to pour [something] into [something], but missing so it spills next to it",
+    "164": "Turning [something] upside down",
+    "165": "Turning the camera downwards while filming [something]",
+    "166": "Turning the camera left while filming [something]",
+    "167": "Turning the camera right while filming [something]",
+    "168": "Turning the camera upwards while filming [something]",
+    "169": "Twisting (wringing) [something] wet until water comes out",
+    "170": "Twisting [something]",
+    "171": "Uncovering [something]",
+    "172": "Unfolding [something]",
+    "173": "Wiping [something] off of [something]"
+  },
+  "image_size": 384,
+  "in_chans": 3,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_150": 150,
+    "LABEL_151": 151,
+    "LABEL_152": 152,
+    "LABEL_153": 153,
+    "LABEL_154": 154,
+    "LABEL_155": 155,
+    "LABEL_156": 156,
+    "LABEL_157": 157,
+    "LABEL_158": 158,
+    "LABEL_159": 159,
+    "LABEL_16": 16,
+    "LABEL_160": 160,
+    "LABEL_161": 161,
+    "LABEL_162": 162,
+    "LABEL_163": 163,
+    "LABEL_164": 164,
+    "LABEL_165": 165,
+    "LABEL_166": 166,
+    "LABEL_167": 167,
+    "LABEL_168": 168,
+    "LABEL_169": 169,
+    "LABEL_17": 17,
+    "LABEL_170": 170,
+    "LABEL_171": 171,
+    "LABEL_172": 172,
+    "LABEL_173": 173,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratio": 4.363636363636363,
+  "model_type": "vjepa2",
+  "num_attention_heads": 22,
+  "num_hidden_layers": 40,
+  "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,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0.dev0",
+  "tubelet_size": 2,
+  "wide_SiLU": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb15cc4a23907575ec2205e20e0b6997692a9ade3a12afdaf8a2f04f9ce5a72b
+size 4512302192

video_preprocessor_config.json

@@ -0,0 +1,79 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device"
+  ],
+  "crop_size": {
+    "height": 384,
+    "width": 384
+  },
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": true,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": null,
+  "fps": null,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "input_data_format": null,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "do_sample_frames",
+    "video_metadata",
+    "fps",
+    "num_frames"
+  ],
+  "num_frames": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 438
+  },
+  "size_divisor": null,
+  "video_metadata": null,
+  "video_processor_type": "VJEPA2VideoProcessor"
+}