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 +1,142 @@
+{
+  "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": "brush_hair",
+    "1": "cartwheel",
+    "2": "catch",
+    "3": "chew",
+    "4": "clap",
+    "5": "climb",
+    "6": "climb_stairs",
+    "7": "dive",
+    "8": "draw_sword",
+    "9": "dribble",
+    "10": "drink",
+    "11": "eat",
+    "12": "fall_floor",
+    "13": "fencing",
+    "14": "flic_flac",
+    "15": "golf",
+    "16": "handstand",
+    "17": "hit",
+    "18": "hug",
+    "19": "jump",
+    "20": "kick",
+    "21": "kick_ball",
+    "22": "kiss",
+    "23": "laugh",
+    "24": "pick",
+    "25": "pour",
+    "26": "pullup",
+    "27": "punch",
+    "28": "push",
+    "29": "pushup",
+    "30": "ride_bike",
+    "31": "ride_horse",
+    "32": "run",
+    "33": "shake_hands",
+    "34": "shoot_ball",
+    "35": "shoot_bow",
+    "36": "shoot_gun",
+    "37": "sit",
+    "38": "situp",
+    "39": "smile",
+    "40": "smoke",
+    "41": "somersault",
+    "42": "stand",
+    "43": "swing_baseball",
+    "44": "sword",
+    "45": "sword_exercise",
+    "46": "talk",
+    "47": "throw",
+    "48": "turn",
+    "49": "walk",
+    "50": "wave"
+  },
+  "image_size": 256,
+  "in_chans": 3,
+  "initializer_range": 0.02,
+  "label2id": {
+    "brush_hair": 0,
+    "cartwheel": 1,
+    "catch": 2,
+    "chew": 3,
+    "clap": 4,
+    "climb": 5,
+    "climb_stairs": 6,
+    "dive": 7,
+    "draw_sword": 8,
+    "dribble": 9,
+    "drink": 10,
+    "eat": 11,
+    "fall_floor": 12,
+    "fencing": 13,
+    "flic_flac": 14,
+    "golf": 15,
+    "handstand": 16,
+    "hit": 17,
+    "hug": 18,
+    "jump": 19,
+    "kick": 20,
+    "kick_ball": 21,
+    "kiss": 22,
+    "laugh": 23,
+    "pick": 24,
+    "pour": 25,
+    "pullup": 26,
+    "punch": 27,
+    "push": 28,
+    "pushup": 29,
+    "ride_bike": 30,
+    "ride_horse": 31,
+    "run": 32,
+    "shake_hands": 33,
+    "shoot_ball": 34,
+    "shoot_bow": 35,
+    "shoot_gun": 36,
+    "sit": 37,
+    "situp": 38,
+    "smile": 39,
+    "smoke": 40,
+    "somersault": 41,
+    "stand": 42,
+    "swing_baseball": 43,
+    "sword": 44,
+    "sword_exercise": 45,
+    "talk": 46,
+    "throw": 47,
+    "turn": 48,
+    "walk": 49,
+    "wave": 50
+  },
+  "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": "4.53.1",
+  "tubelet_size": 2,
+  "use_SiLU": false,
+  "wide_SiLU": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615b87fc5cdc961b959cac469fe353e7d0b885cb720eb7594238d5430f2ae9e4
+size 1501514284