Upload tokenizer

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]

merges.txt

@@ -0,0 +1 @@
+#version: 0.2

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,357 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "</s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "</s>": {
+        "id": "</s>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "</s>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": "",
+    "end_of_word_suffix": "",
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<pad>": 0,
+      "</s>": 1,
+      "!": 2,
+      "\"": 3,
+      "#": 4,
+      "$": 5,
+      "%": 6,
+      "&": 7,
+      "'": 8,
+      "(": 9,
+      ")": 10,
+      "*": 11,
+      "+": 12,
+      ",": 13,
+      "-": 14,
+      ".": 15,
+      "/": 16,
+      "0": 17,
+      "1": 18,
+      "2": 19,
+      "3": 20,
+      "4": 21,
+      "5": 22,
+      "6": 23,
+      "7": 24,
+      "8": 25,
+      "9": 26,
+      ":": 27,
+      ";": 28,
+      "<": 29,
+      "=": 30,
+      ">": 31,
+      "?": 32,
+      "@": 33,
+      "A": 34,
+      "B": 35,
+      "C": 36,
+      "D": 37,
+      "E": 38,
+      "F": 39,
+      "G": 40,
+      "H": 41,
+      "I": 42,
+      "J": 43,
+      "K": 44,
+      "L": 45,
+      "M": 46,
+      "N": 47,
+      "O": 48,
+      "P": 49,
+      "Q": 50,
+      "R": 51,
+      "S": 52,
+      "T": 53,
+      "U": 54,
+      "V": 55,
+      "W": 56,
+      "X": 57,
+      "Y": 58,
+      "Z": 59,
+      "[": 60,
+      "\\": 61,
+      "]": 62,
+      "^": 63,
+      "_": 64,
+      "`": 65,
+      "a": 66,
+      "b": 67,
+      "c": 68,
+      "d": 69,
+      "e": 70,
+      "f": 71,
+      "g": 72,
+      "h": 73,
+      "i": 74,
+      "j": 75,
+      "k": 76,
+      "l": 77,
+      "m": 78,
+      "n": 79,
+      "o": 80,
+      "p": 81,
+      "q": 82,
+      "r": 83,
+      "s": 84,
+      "t": 85,
+      "u": 86,
+      "v": 87,
+      "w": 88,
+      "x": 89,
+      "y": 90,
+      "z": 91,
+      "{": 92,
+      "|": 93,
+      "}": 94,
+      "~": 95,
+      "¡": 96,
+      "¢": 97,
+      "£": 98,
+      "¤": 99,
+      "¥": 100,
+      "¦": 101,
+      "§": 102,
+      "¨": 103,
+      "©": 104,
+      "ª": 105,
+      "«": 106,
+      "¬": 107,
+      "®": 108,
+      "¯": 109,
+      "°": 110,
+      "±": 111,
+      "²": 112,
+      "³": 113,
+      "´": 114,
+      "µ": 115,
+      "¶": 116,
+      "·": 117,
+      "¸": 118,
+      "¹": 119,
+      "º": 120,
+      "»": 121,
+      "¼": 122,
+      "½": 123,
+      "¾": 124,
+      "¿": 125,
+      "À": 126,
+      "Á": 127,
+      "Â": 128,
+      "Ã": 129,
+      "Ä": 130,
+      "Å": 131,
+      "Æ": 132,
+      "Ç": 133,
+      "È": 134,
+      "É": 135,
+      "Ê": 136,
+      "Ë": 137,
+      "Ì": 138,
+      "Í": 139,
+      "Î": 140,
+      "Ï": 141,
+      "Ð": 142,
+      "Ñ": 143,
+      "Ò": 144,
+      "Ó": 145,
+      "Ô": 146,
+      "Õ": 147,
+      "Ö": 148,
+      "×": 149,
+      "Ø": 150,
+      "Ù": 151,
+      "Ú": 152,
+      "Û": 153,
+      "Ü": 154,
+      "Ý": 155,
+      "Þ": 156,
+      "ß": 157,
+      "à": 158,
+      "á": 159,
+      "â": 160,
+      "ã": 161,
+      "ä": 162,
+      "å": 163,
+      "æ": 164,
+      "ç": 165,
+      "è": 166,
+      "é": 167,
+      "ê": 168,
+      "ë": 169,
+      "ì": 170,
+      "í": 171,
+      "î": 172,
+      "ï": 173,
+      "ð": 174,
+      "ñ": 175,
+      "ò": 176,
+      "ó": 177,
+      "ô": 178,
+      "õ": 179,
+      "ö": 180,
+      "÷": 181,
+      "ø": 182,
+      "ù": 183,
+      "ú": 184,
+      "û": 185,
+      "ü": 186,
+      "ý": 187,
+      "þ": 188,
+      "ÿ": 189,
+      "Ā": 190,
+      "ā": 191,
+      "Ă": 192,
+      "ă": 193,
+      "Ą": 194,
+      "ą": 195,
+      "Ć": 196,
+      "ć": 197,
+      "Ĉ": 198,
+      "ĉ": 199,
+      "Ċ": 200,
+      "ċ": 201,
+      "Č": 202,
+      "č": 203,
+      "Ď": 204,
+      "ď": 205,
+      "Đ": 206,
+      "đ": 207,
+      "Ē": 208,
+      "ē": 209,
+      "Ĕ": 210,
+      "ĕ": 211,
+      "Ė": 212,
+      "ė": 213,
+      "Ę": 214,
+      "ę": 215,
+      "Ě": 216,
+      "ě": 217,
+      "Ĝ": 218,
+      "ĝ": 219,
+      "Ğ": 220,
+      "ğ": 221,
+      "Ġ": 222,
+      "ġ": 223,
+      "Ģ": 224,
+      "ģ": 225,
+      "Ĥ": 226,
+      "ĥ": 227,
+      "Ħ": 228,
+      "ħ": 229,
+      "Ĩ": 230,
+      "ĩ": 231,
+      "Ī": 232,
+      "ī": 233,
+      "Ĭ": 234,
+      "ĭ": 235,
+      "Į": 236,
+      "į": 237,
+      "İ": 238,
+      "ı": 239,
+      "IJ": 240,
+      "ij": 241,
+      "Ĵ": 242,
+      "ĵ": 243,
+      "Ķ": 244,
+      "ķ": 245,
+      "ĸ": 246,
+      "Ĺ": 247,
+      "ĺ": 248,
+      "Ļ": 249,
+      "ļ": 250,
+      "Ľ": 251,
+      "ľ": 252,
+      "Ŀ": 253,
+      "ŀ": 254,
+      "Ł": 255,
+      "ł": 256,
+      "Ń": 257
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

vocab.json

@@ -0,0 +1 @@
+{"<pad>":0,"</s>":1,"!":2,"\"":3,"#":4,"$":5,"%":6,"&":7,"'":8,"(":9,")":10,"*":11,"+":12,",":13,"-":14,".":15,"/":16,"0":17,"1":18,"2":19,"3":20,"4":21,"5":22,"6":23,"7":24,"8":25,"9":26,":":27,";":28,"<":29,"=":30,">":31,"?":32,"@":33,"A":34,"B":35,"C":36,"D":37,"E":38,"F":39,"G":40,"H":41,"I":42,"J":43,"K":44,"L":45,"M":46,"N":47,"O":48,"P":49,"Q":50,"R":51,"S":52,"T":53,"U":54,"V":55,"W":56,"X":57,"Y":58,"Z":59,"[":60,"\\":61,"]":62,"^":63,"_":64,"`":65,"a":66,"b":67,"c":68,"d":69,"e":70,"f":71,"g":72,"h":73,"i":74,"j":75,"k":76,"l":77,"m":78,"n":79,"o":80,"p":81,"q":82,"r":83,"s":84,"t":85,"u":86,"v":87,"w":88,"x":89,"y":90,"z":91,"{":92,"|":93,"}":94,"~":95,"¡":96,"¢":97,"£":98,"¤":99,"¥":100,"¦":101,"§":102,"¨":103,"©":104,"ª":105,"«":106,"¬":107,"®":108,"¯":109,"°":110,"±":111,"²":112,"³":113,"´":114,"µ":115,"¶":116,"·":117,"¸":118,"¹":119,"º":120,"»":121,"¼":122,"½":123,"¾":124,"¿":125,"À":126,"Á":127,"Â":128,"Ã":129,"Ä":130,"Å":131,"Æ":132,"Ç":133,"È":134,"É":135,"Ê":136,"Ë":137,"Ì":138,"Í":139,"Î":140,"Ï":141,"Ð":142,"Ñ":143,"Ò":144,"Ó":145,"Ô":146,"Õ":147,"Ö":148,"×":149,"Ø":150,"Ù":151,"Ú":152,"Û":153,"Ü":154,"Ý":155,"Þ":156,"ß":157,"à":158,"á":159,"â":160,"ã":161,"ä":162,"å":163,"æ":164,"ç":165,"è":166,"é":167,"ê":168,"ë":169,"ì":170,"í":171,"î":172,"ï":173,"ð":174,"ñ":175,"ò":176,"ó":177,"ô":178,"õ":179,"ö":180,"÷":181,"ø":182,"ù":183,"ú":184,"û":185,"ü":186,"ý":187,"þ":188,"ÿ":189,"Ā":190,"ā":191,"Ă":192,"ă":193,"Ą":194,"ą":195,"Ć":196,"ć":197,"Ĉ":198,"ĉ":199,"Ċ":200,"ċ":201,"Č":202,"č":203,"Ď":204,"ď":205,"Đ":206,"đ":207,"Ē":208,"ē":209,"Ĕ":210,"ĕ":211,"Ė":212,"ė":213,"Ę":214,"ę":215,"Ě":216,"ě":217,"Ĝ":218,"ĝ":219,"Ğ":220,"ğ":221,"Ġ":222,"ġ":223,"Ģ":224,"ģ":225,"Ĥ":226,"ĥ":227,"Ħ":228,"ħ":229,"Ĩ":230,"ĩ":231,"Ī":232,"ī":233,"Ĭ":234,"ĭ":235,"Į":236,"į":237,"İ":238,"ı":239,"IJ":240,"ij":241,"Ĵ":242,"ĵ":243,"Ķ":244,"ķ":245,"ĸ":246,"Ĺ":247,"ĺ":248,"Ļ":249,"ļ":250,"Ľ":251,"ľ":252,"Ŀ":253,"ŀ":254,"Ł":255,"ł":256,"Ń":257}