Upload DebertaV2ForTokenClassification

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 +1,261 @@
+{
+  "_name_or_path": "Isotonic/deberta-v3-base_finetuned_ai4privacy_v2",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "None",
+    "1": "B-CITY",
+    "2": "I-CITY",
+    "3": "B-FIRSTNAME",
+    "4": "I-FIRSTNAME",
+    "5": "None",
+    "6": "None",
+    "7": "None",
+    "8": "None",
+    "9": "None",
+    "10": "B-LASTNAME",
+    "11": "B-EMAIL",
+    "12": "I-EMAIL",
+    "13": "None",
+    "14": "None",
+    "15": "B-ACCOUNTNUMBER",
+    "16": "I-ACCOUNTNUMBER",
+    "17": "B-ACCOUNTNAME",
+    "18": "I-ACCOUNTNAME",
+    "19": "B-MIDDLENAME",
+    "20": "I-MIDDLENAME",
+    "21": "None",
+    "22": "None",
+    "23": "None",
+    "24": "None",
+    "25": "None",
+    "26": "None",
+    "27": "None",
+    "28": "None",
+    "29": "None",
+    "30": "None",
+    "31": "None",
+    "32": "B-STATE",
+    "33": "B-COMPANYNAME",
+    "34": "I-COMPANYNAME",
+    "35": "None",
+    "36": "None",
+    "37": "B-STREET",
+    "38": "I-STREET",
+    "39": "None",
+    "40": "None",
+    "41": "None",
+    "42": "None",
+    "43": "None",
+    "44": "None",
+    "45": "None",
+    "46": "None",
+    "47": "None",
+    "48": "None",
+    "49": "None",
+    "50": "None",
+    "51": "None",
+    "52": "None",
+    "53": "None",
+    "54": "None",
+    "55": "None",
+    "56": "None",
+    "57": "None",
+    "58": "None",
+    "59": "None",
+    "60": "None",
+    "61": "None",
+    "62": "None",
+    "63": "None",
+    "64": "None",
+    "65": "None",
+    "66": "None",
+    "67": "None",
+    "68": "None",
+    "69": "None",
+    "70": "None",
+    "71": "None",
+    "72": "I-LASTNAME",
+    "73": "B-PHONENUMBER",
+    "74": "I-PHONENUMBER",
+    "75": "None",
+    "76": "None",
+    "77": "B-SECONDARYADDRESS",
+    "78": "I-SECONDARYADDRESS",
+    "79": "B-ZIPCODE",
+    "80": "I-ZIPCODE",
+    "81": "None",
+    "82": "None",
+    "83": "None",
+    "84": "None",
+    "85": "None",
+    "86": "None",
+    "87": "None",
+    "88": "None",
+    "89": "None",
+    "90": "None",
+    "91": "None",
+    "92": "B-BUILDINGNUMBER",
+    "93": "I-BUILDINGNUMBER",
+    "94": "None",
+    "95": "None",
+    "96": "None",
+    "97": "None",
+    "98": "None",
+    "99": "None",
+    "100": "None",
+    "101": "None",
+    "102": "None",
+    "103": "None",
+    "104": "None",
+    "105": "None",
+    "106": "None",
+    "107": "None",
+    "108": "None",
+    "109": "None",
+    "110": "None"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACCOUNTNAME": 17,
+    "B-ACCOUNTNUMBER": 15,
+    "B-AGE": 23,
+    "B-AMOUNT": 94,
+    "B-BIC": 99,
+    "B-BITCOINADDRESS": 63,
+    "B-BUILDINGNUMBER": 92,
+    "B-CITY": 1,
+    "B-COMPANYNAME": 33,
+    "B-COUNTY": 21,
+    "B-CREDITCARDCVV": 24,
+    "B-CREDITCARDISSUER": 75,
+    "B-CREDITCARDNUMBER": 68,
+    "B-CURRENCY": 104,
+    "B-CURRENCYCODE": 106,
+    "B-CURRENCYNAME": 102,
+    "B-CURRENCYSYMBOL": 53,
+    "B-DATE": 54,
+    "B-DOB": 25,
+    "B-EMAIL": 11,
+    "B-ETHEREUMADDRESS": 61,
+    "B-EYECOLOR": 101,
+    "B-FIRSTNAME": 3,
+    "B-GENDER": 84,
+    "B-HEIGHT": 88,
+    "B-IBAN": 97,
+    "B-IP": 49,
+    "B-IPV4": 41,
+    "B-IPV6": 70,
+    "B-JOBAREA": 87,
+    "B-JOBTITLE": 90,
+    "B-JOBTYPE": 7,
+    "B-LASTNAME": 10,
+    "B-LITECOINADDRESS": 65,
+    "B-MAC": 45,
+    "B-MASKEDNUMBER": 27,
+    "B-MIDDLENAME": 19,
+    "B-NEARBYGPSCOORDINATE": 13,
+    "B-ORDINALDIRECTION": 86,
+    "B-PASSWORD": 29,
+    "B-PHONEIMEI": 35,
+    "B-PHONENUMBER": 73,
+    "B-PIN": 47,
+    "B-PREFIX": 8,
+    "B-SECONDARYADDRESS": 77,
+    "B-SEX": 31,
+    "B-SSN": 39,
+    "B-STATE": 32,
+    "B-STREET": 37,
+    "B-TIME": 56,
+    "B-URL": 51,
+    "B-USERAGENT": 43,
+    "B-USERNAME": 5,
+    "B-VEHICLEVIN": 81,
+    "B-VEHICLEVRM": 58,
+    "B-ZIPCODE": 79,
+    "I-ACCOUNTNAME": 18,
+    "I-ACCOUNTNUMBER": 16,
+    "I-AGE": 83,
+    "I-AMOUNT": 60,
+    "I-BIC": 100,
+    "I-BITCOINADDRESS": 64,
+    "I-BUILDINGNUMBER": 93,
+    "I-CITY": 2,
+    "I-COMPANYNAME": 34,
+    "I-COUNTY": 22,
+    "I-CREDITCARDCVV": 110,
+    "I-CREDITCARDISSUER": 76,
+    "I-CREDITCARDNUMBER": 69,
+    "I-CURRENCY": 105,
+    "I-CURRENCYCODE": 107,
+    "I-CURRENCYNAME": 103,
+    "I-CURRENCYSYMBOL": 96,
+    "I-DATE": 55,
+    "I-DOB": 26,
+    "I-EMAIL": 12,
+    "I-ETHEREUMADDRESS": 62,
+    "I-EYECOLOR": 109,
+    "I-FIRSTNAME": 4,
+    "I-GENDER": 85,
+    "I-HEIGHT": 89,
+    "I-IBAN": 98,
+    "I-IP": 50,
+    "I-IPV4": 42,
+    "I-IPV6": 71,
+    "I-JOBAREA": 108,
+    "I-JOBTITLE": 91,
+    "I-JOBTYPE": 67,
+    "I-LASTNAME": 72,
+    "I-LITECOINADDRESS": 66,
+    "I-MAC": 46,
+    "I-MASKEDNUMBER": 28,
+    "I-MIDDLENAME": 20,
+    "I-NEARBYGPSCOORDINATE": 14,
+    "I-PASSWORD": 30,
+    "I-PHONEIMEI": 36,
+    "I-PHONENUMBER": 74,
+    "I-PIN": 48,
+    "I-PREFIX": 9,
+    "I-SECONDARYADDRESS": 78,
+    "I-SSN": 40,
+    "I-STATE": 95,
+    "I-STREET": 38,
+    "I-TIME": 57,
+    "I-URL": 52,
+    "I-USERAGENT": 44,
+    "I-USERNAME": 6,
+    "I-VEHICLEVIN": 82,
+    "I-VEHICLEVRM": 59,
+    "I-ZIPCODE": 80,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179e55224bbc3ff4521c89e7c2e7cad1e7074c73b37eedd1cfde0c79848f2862
+size 735692028