Upload CustomViltForVQA

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 +1,249 @@
+{
+  "_name_or_path": "dandelin/vilt-b32-finetuned-vqa",
+  "architectures": [
+    "CustomViltForVQA"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "potted plant",
+    "1": "cell phone",
+    "2": "stop sign",
+    "3": "dog",
+    "4": "laptop",
+    "5": "frisbee",
+    "6": "sports ball",
+    "7": "cup",
+    "8": "mouse",
+    "9": "elephant",
+    "10": "3",
+    "11": "toothbrush",
+    "12": "vase",
+    "13": "airplane",
+    "14": "right",
+    "15": "Behind",
+    "16": "Front",
+    "17": "skateboard",
+    "18": "knife",
+    "19": "toilet",
+    "20": "No",
+    "21": "left",
+    "22": "Brown",
+    "23": "cow",
+    "24": "bear",
+    "25": "boat",
+    "26": "bird",
+    "27": "skis",
+    "28": "baseball glove",
+    "29": "oven",
+    "30": "Grey",
+    "31": "parking meter",
+    "32": "horse",
+    "33": "couch",
+    "34": "orange",
+    "35": "White",
+    "36": "Purple",
+    "37": "Left",
+    "38": "surfboard",
+    "39": "truck",
+    "40": "tv",
+    "41": "traffic light",
+    "42": "pizza",
+    "43": "banana",
+    "44": "tie",
+    "45": "train",
+    "46": "remote",
+    "47": "bottle",
+    "48": "bus",
+    "49": "Blue",
+    "50": "person",
+    "51": "tennis racket",
+    "52": "broccoli",
+    "53": "bed",
+    "54": "4",
+    "55": "keyboard",
+    "56": "cat",
+    "57": "sink",
+    "58": "Yes",
+    "59": "dining table",
+    "60": "cake",
+    "61": "Green",
+    "62": "snowboard",
+    "63": "Above",
+    "64": "Right",
+    "65": "above",
+    "66": "giraffe",
+    "67": "refrigerator",
+    "68": "9",
+    "69": "kite",
+    "70": "book",
+    "71": "suitcase",
+    "72": "bicycle",
+    "73": "motorcycle",
+    "74": "1",
+    "75": "2",
+    "76": "carrot",
+    "77": "6",
+    "78": "Black",
+    "79": "5",
+    "80": "wine glass",
+    "81": "8",
+    "82": "7",
+    "83": "scissors",
+    "84": "sheep",
+    "85": "sandwich",
+    "86": "clock",
+    "87": "handbag",
+    "88": "hot dog",
+    "89": "bowl",
+    "90": "Pink",
+    "91": "chair",
+    "92": "fire hydrant",
+    "93": "donut",
+    "94": "fork",
+    "95": "0",
+    "96": "Red",
+    "97": "teddy bear",
+    "98": "apple",
+    "99": "Yellow",
+    "100": "bench",
+    "101": "baseball bat",
+    "102": "umbrella",
+    "103": "zebra",
+    "104": "spoon",
+    "105": "Orange",
+    "106": "Below",
+    "107": "car"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 95,
+    "1": 74,
+    "2": 75,
+    "3": 10,
+    "4": 54,
+    "5": 79,
+    "6": 77,
+    "7": 82,
+    "8": 81,
+    "9": 68,
+    "Above": 63,
+    "Behind": 15,
+    "Below": 106,
+    "Black": 78,
+    "Blue": 49,
+    "Brown": 22,
+    "Front": 16,
+    "Green": 61,
+    "Grey": 30,
+    "Left": 37,
+    "No": 20,
+    "Orange": 105,
+    "Pink": 90,
+    "Purple": 36,
+    "Red": 96,
+    "Right": 64,
+    "White": 35,
+    "Yellow": 99,
+    "Yes": 58,
+    "above": 65,
+    "airplane": 13,
+    "apple": 98,
+    "banana": 43,
+    "baseball bat": 101,
+    "baseball glove": 28,
+    "bear": 24,
+    "bed": 53,
+    "bench": 100,
+    "bicycle": 72,
+    "bird": 26,
+    "boat": 25,
+    "book": 70,
+    "bottle": 47,
+    "bowl": 89,
+    "broccoli": 52,
+    "bus": 48,
+    "cake": 60,
+    "car": 107,
+    "carrot": 76,
+    "cat": 56,
+    "cell phone": 1,
+    "chair": 91,
+    "clock": 86,
+    "couch": 33,
+    "cow": 23,
+    "cup": 7,
+    "dining table": 59,
+    "dog": 3,
+    "donut": 93,
+    "elephant": 9,
+    "fire hydrant": 92,
+    "fork": 94,
+    "frisbee": 5,
+    "giraffe": 66,
+    "handbag": 87,
+    "horse": 32,
+    "hot dog": 88,
+    "keyboard": 55,
+    "kite": 69,
+    "knife": 18,
+    "laptop": 4,
+    "left": 21,
+    "motorcycle": 73,
+    "mouse": 8,
+    "orange": 34,
+    "oven": 29,
+    "parking meter": 31,
+    "person": 50,
+    "pizza": 42,
+    "potted plant": 0,
+    "refrigerator": 67,
+    "remote": 46,
+    "right": 14,
+    "sandwich": 85,
+    "scissors": 83,
+    "sheep": 84,
+    "sink": 57,
+    "skateboard": 17,
+    "skis": 27,
+    "snowboard": 62,
+    "spoon": 104,
+    "sports ball": 6,
+    "stop sign": 2,
+    "suitcase": 71,
+    "surfboard": 38,
+    "teddy bear": 97,
+    "tennis racket": 51,
+    "tie": 44,
+    "toilet": 19,
+    "toothbrush": 11,
+    "traffic light": 41,
+    "train": 45,
+    "truck": 39,
+    "tv": 40,
+    "umbrella": 102,
+    "vase": 12,
+    "wine glass": 80,
+    "zebra": 103
+  },
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c2d34454baed6f5e6e338be3937ff748194cca397ecec7b65f353b824b8cb8
+size 446736704