Upload DistilBertForTokenClassification

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 +1,255 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-PHONEIMEI",
+    "2": "I-PHONEIMEI",
+    "3": "B-JOBAREA",
+    "4": "I-JOBAREA",
+    "5": "B-FIRSTNAME",
+    "6": "B-VEHICLEVIN",
+    "7": "I-VEHICLEVIN",
+    "8": "I-FIRSTNAME",
+    "9": "B-AGE",
+    "10": "B-GENDER",
+    "11": "I-GENDER",
+    "12": "B-HEIGHT",
+    "13": "I-HEIGHT",
+    "14": "B-BUILDINGNUMBER",
+    "15": "I-BUILDINGNUMBER",
+    "16": "B-MASKEDNUMBER",
+    "17": "I-MASKEDNUMBER",
+    "18": "B-PASSWORD",
+    "19": "I-PASSWORD",
+    "20": "B-DOB",
+    "21": "I-DOB",
+    "22": "B-IPV6",
+    "23": "I-IPV6",
+    "24": "B-NEARBYGPSCOORDINATE",
+    "25": "I-NEARBYGPSCOORDINATE",
+    "26": "B-USERAGENT",
+    "27": "I-USERAGENT",
+    "28": "B-TIME",
+    "29": "I-TIME",
+    "30": "B-JOBTITLE",
+    "31": "I-JOBTITLE",
+    "32": "B-COUNTY",
+    "33": "B-EMAIL",
+    "34": "I-EMAIL",
+    "35": "B-ACCOUNTNUMBER",
+    "36": "I-ACCOUNTNUMBER",
+    "37": "B-PIN",
+    "38": "I-PIN",
+    "39": "B-EYECOLOR",
+    "40": "I-EYECOLOR",
+    "41": "B-LASTNAME",
+    "42": "I-LASTNAME",
+    "43": "B-IPV4",
+    "44": "I-IPV4",
+    "45": "B-DATE",
+    "46": "I-DATE",
+    "47": "B-STREET",
+    "48": "I-STREET",
+    "49": "B-CITY",
+    "50": "I-CITY",
+    "51": "B-PREFIX",
+    "52": "I-PREFIX",
+    "53": "B-MIDDLENAME",
+    "54": "B-CREDITCARDISSUER",
+    "55": "B-CREDITCARDNUMBER",
+    "56": "I-CREDITCARDNUMBER",
+    "57": "I-CREDITCARDISSUER",
+    "58": "B-STATE",
+    "59": "B-VEHICLEVRM",
+    "60": "I-VEHICLEVRM",
+    "61": "B-ORDINALDIRECTION",
+    "62": "B-SEX",
+    "63": "B-JOBTYPE",
+    "64": "I-JOBTYPE",
+    "65": "B-CURRENCYCODE",
+    "66": "I-CURRENCYCODE",
+    "67": "B-CURRENCYSYMBOL",
+    "68": "B-AMOUNT",
+    "69": "I-AMOUNT",
+    "70": "B-ACCOUNTNAME",
+    "71": "I-ACCOUNTNAME",
+    "72": "I-STATE",
+    "73": "B-BITCOINADDRESS",
+    "74": "I-BITCOINADDRESS",
+    "75": "B-LITECOINADDRESS",
+    "76": "I-LITECOINADDRESS",
+    "77": "B-PHONENUMBER",
+    "78": "I-PHONENUMBER",
+    "79": "B-MAC",
+    "80": "I-MAC",
+    "81": "B-CURRENCY",
+    "82": "B-IBAN",
+    "83": "I-IBAN",
+    "84": "B-COMPANYNAME",
+    "85": "I-COMPANYNAME",
+    "86": "B-CURRENCYNAME",
+    "87": "I-CURRENCYNAME",
+    "88": "I-CURRENCYSYMBOL",
+    "89": "B-ZIPCODE",
+    "90": "I-ZIPCODE",
+    "91": "B-SSN",
+    "92": "I-SSN",
+    "93": "I-CURRENCY",
+    "94": "B-URL",
+    "95": "I-URL",
+    "96": "B-IP",
+    "97": "I-IP",
+    "98": "B-SECONDARYADDRESS",
+    "99": "I-SECONDARYADDRESS",
+    "100": "B-USERNAME",
+    "101": "I-USERNAME",
+    "102": "B-ETHEREUMADDRESS",
+    "103": "I-ETHEREUMADDRESS",
+    "104": "B-CREDITCARDCVV",
+    "105": "I-AGE",
+    "106": "I-MIDDLENAME",
+    "107": "I-COUNTY",
+    "108": "B-BIC",
+    "109": "I-BIC",
+    "110": "I-CREDITCARDCVV",
+    "111": "I-ORDINALDIRECTION",
+    "112": "I-SEX"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-ACCOUNTNAME": 70,
+    "B-ACCOUNTNUMBER": 35,
+    "B-AGE": 9,
+    "B-AMOUNT": 68,
+    "B-BIC": 108,
+    "B-BITCOINADDRESS": 73,
+    "B-BUILDINGNUMBER": 14,
+    "B-CITY": 49,
+    "B-COMPANYNAME": 84,
+    "B-COUNTY": 32,
+    "B-CREDITCARDCVV": 104,
+    "B-CREDITCARDISSUER": 54,
+    "B-CREDITCARDNUMBER": 55,
+    "B-CURRENCY": 81,
+    "B-CURRENCYCODE": 65,
+    "B-CURRENCYNAME": 86,
+    "B-CURRENCYSYMBOL": 67,
+    "B-DATE": 45,
+    "B-DOB": 20,
+    "B-EMAIL": 33,
+    "B-ETHEREUMADDRESS": 102,
+    "B-EYECOLOR": 39,
+    "B-FIRSTNAME": 5,
+    "B-GENDER": 10,
+    "B-HEIGHT": 12,
+    "B-IBAN": 82,
+    "B-IP": 96,
+    "B-IPV4": 43,
+    "B-IPV6": 22,
+    "B-JOBAREA": 3,
+    "B-JOBTITLE": 30,
+    "B-JOBTYPE": 63,
+    "B-LASTNAME": 41,
+    "B-LITECOINADDRESS": 75,
+    "B-MAC": 79,
+    "B-MASKEDNUMBER": 16,
+    "B-MIDDLENAME": 53,
+    "B-NEARBYGPSCOORDINATE": 24,
+    "B-ORDINALDIRECTION": 61,
+    "B-PASSWORD": 18,
+    "B-PHONEIMEI": 1,
+    "B-PHONENUMBER": 77,
+    "B-PIN": 37,
+    "B-PREFIX": 51,
+    "B-SECONDARYADDRESS": 98,
+    "B-SEX": 62,
+    "B-SSN": 91,
+    "B-STATE": 58,
+    "B-STREET": 47,
+    "B-TIME": 28,
+    "B-URL": 94,
+    "B-USERAGENT": 26,
+    "B-USERNAME": 100,
+    "B-VEHICLEVIN": 6,
+    "B-VEHICLEVRM": 59,
+    "B-ZIPCODE": 89,
+    "I-ACCOUNTNAME": 71,
+    "I-ACCOUNTNUMBER": 36,
+    "I-AGE": 105,
+    "I-AMOUNT": 69,
+    "I-BIC": 109,
+    "I-BITCOINADDRESS": 74,
+    "I-BUILDINGNUMBER": 15,
+    "I-CITY": 50,
+    "I-COMPANYNAME": 85,
+    "I-COUNTY": 107,
+    "I-CREDITCARDCVV": 110,
+    "I-CREDITCARDISSUER": 57,
+    "I-CREDITCARDNUMBER": 56,
+    "I-CURRENCY": 93,
+    "I-CURRENCYCODE": 66,
+    "I-CURRENCYNAME": 87,
+    "I-CURRENCYSYMBOL": 88,
+    "I-DATE": 46,
+    "I-DOB": 21,
+    "I-EMAIL": 34,
+    "I-ETHEREUMADDRESS": 103,
+    "I-EYECOLOR": 40,
+    "I-FIRSTNAME": 8,
+    "I-GENDER": 11,
+    "I-HEIGHT": 13,
+    "I-IBAN": 83,
+    "I-IP": 97,
+    "I-IPV4": 44,
+    "I-IPV6": 23,
+    "I-JOBAREA": 4,
+    "I-JOBTITLE": 31,
+    "I-JOBTYPE": 64,
+    "I-LASTNAME": 42,
+    "I-LITECOINADDRESS": 76,
+    "I-MAC": 80,
+    "I-MASKEDNUMBER": 17,
+    "I-MIDDLENAME": 106,
+    "I-NEARBYGPSCOORDINATE": 25,
+    "I-ORDINALDIRECTION": 111,
+    "I-PASSWORD": 19,
+    "I-PHONEIMEI": 2,
+    "I-PHONENUMBER": 78,
+    "I-PIN": 38,
+    "I-PREFIX": 52,
+    "I-SECONDARYADDRESS": 99,
+    "I-SEX": 112,
+    "I-SSN": 92,
+    "I-STATE": 72,
+    "I-STREET": 48,
+    "I-TIME": 29,
+    "I-URL": 95,
+    "I-USERAGENT": 27,
+    "I-USERNAME": 101,
+    "I-VEHICLEVIN": 7,
+    "I-VEHICLEVRM": 60,
+    "I-ZIPCODE": 90,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e0553d72602967fe6a0326ac775d8d78dd0fa2c6a6d2998f17e4e17135cae7
+size 261123580