Upload ViTForImageClassification

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 +1,117 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "dtype": "float32",
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "01_ka",
+    "10": "1",
+    "11": "10_na(02)",
+    "12": "11_ta(01)",
+    "13": "12_tha(01)",
+    "14": "13_da(01)",
+    "15": "14_dha(01)",
+    "16": "15_na(03)",
+    "17": "16_ta(02)",
+    "18": "17_tha(02)",
+    "19": "18_da(02)",
+    "2": "02_kha",
+    "20": "19_dha(02)",
+    "21": "2",
+    "22": "20_na(04)",
+    "23": "21_pa",
+    "24": "22_pha",
+    "25": "23_ba",
+    "26": "24_bha",
+    "27": "25_ma",
+    "28": "26_ya",
+    "29": "27_ra",
+    "3": "03_ga",
+    "30": "28_la(01)",
+    "31": "29_va",
+    "32": "3",
+    "33": "30_la(02)",
+    "34": "31_sa(01)",
+    "35": "32_sa(02)",
+    "36": "33_sa(03)",
+    "37": "34_ha",
+    "38": "4",
+    "39": "5",
+    "4": "04_gha",
+    "40": "6",
+    "41": "7",
+    "42": "8",
+    "43": "9",
+    "5": "05_na(01)",
+    "6": "06_ca",
+    "7": "07_cha",
+    "8": "08_ja",
+    "9": "09_jha"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "0",
+    "01_ka": "1",
+    "02_kha": "2",
+    "03_ga": "3",
+    "04_gha": "4",
+    "05_na(01)": "5",
+    "06_ca": "6",
+    "07_cha": "7",
+    "08_ja": "8",
+    "09_jha": "9",
+    "1": "10",
+    "10_na(02)": "11",
+    "11_ta(01)": "12",
+    "12_tha(01)": "13",
+    "13_da(01)": "14",
+    "14_dha(01)": "15",
+    "15_na(03)": "16",
+    "16_ta(02)": "17",
+    "17_tha(02)": "18",
+    "18_da(02)": "19",
+    "19_dha(02)": "20",
+    "2": "21",
+    "20_na(04)": "22",
+    "21_pa": "23",
+    "22_pha": "24",
+    "23_ba": "25",
+    "24_bha": "26",
+    "25_ma": "27",
+    "26_ya": "28",
+    "27_ra": "29",
+    "28_la(01)": "30",
+    "29_va": "31",
+    "3": "32",
+    "30_la(02)": "33",
+    "31_sa(01)": "34",
+    "32_sa(02)": "35",
+    "33_sa(03)": "36",
+    "34_ha": "37",
+    "4": "38",
+    "5": "39",
+    "6": "40",
+    "7": "41",
+    "8": "42",
+    "9": "43"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b019f57323c8e0b82a9fd7e5328cb6ac4aeb72da1962b78dd7aaf78cd29b993
+size 343353176