Upload tokenizer

README.md

@@ -0,0 +1,201 @@
+---
+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 +1,5 @@
+{
+ "bos_token": "<|endoftext|>",
+ "eos_token": "<|endoftext|>",
+ "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,304 @@
+{
+ "version": "1.0",
+ "truncation": null,
+ "padding": null,
+ "added_tokens": [
+ {
+ "id": 0,
+ "content": "<|endoftext|>",
+ "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": "ByteLevel",
+ "add_prefix_space": true,
+ "trim_offsets": false,
+ "use_regex": true
+ },
+ "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,
+ "vocab": {
+ "<|endoftext|>": 0,
+ "!": 1,
+ "\"": 2,
+ "#": 3,
+ "$": 4,
+ "%": 5,
+ "&": 6,
+ "'": 7,
+ "(": 8,
+ ")": 9,
+ "*": 10,
+ "+": 11,
+ ",": 12,
+ "-": 13,
+ ".": 14,
+ "/": 15,
+ "0": 16,
+ "1": 17,
+ "2": 18,
+ "3": 19,
+ "4": 20,
+ "5": 21,
+ "6": 22,
+ "7": 23,
+ "8": 24,
+ "9": 25,
+ ":": 26,
+ ";": 27,
+ "<": 28,
+ "=": 29,
+ ">": 30,
+ "?": 31,
+ "@": 32,
+ "A": 33,
+ "B": 34,
+ "C": 35,
+ "D": 36,
+ "E": 37,
+ "F": 38,
+ "G": 39,
+ "H": 40,
+ "I": 41,
+ "J": 42,
+ "K": 43,
+ "L": 44,
+ "M": 45,
+ "N": 46,
+ "O": 47,
+ "P": 48,
+ "Q": 49,
+ "R": 50,
+ "S": 51,
+ "T": 52,
+ "U": 53,
+ "V": 54,
+ "W": 55,
+ "X": 56,
+ "Y": 57,
+ "Z": 58,
+ "[": 59,
+ "\\": 60,
+ "]": 61,
+ "^": 62,
+ "_": 63,
+ "`": 64,
+ "a": 65,
+ "b": 66,
+ "c": 67,
+ "d": 68,
+ "e": 69,
+ "f": 70,
+ "g": 71,
+ "h": 72,
+ "i": 73,
+ "j": 74,
+ "k": 75,
+ "l": 76,
+ "m": 77,
+ "n": 78,
+ "o": 79,
+ "p": 80,
+ "q": 81,
+ "r": 82,
+ "s": 83,
+ "t": 84,
+ "u": 85,
+ "v": 86,
+ "w": 87,
+ "x": 88,
+ "y": 89,
+ "z": 90,
+ "{": 91,
+ "|": 92,
+ "}": 93,
+ "~": 94,
+ "¡": 95,
+ "¢": 96,
+ "£": 97,
+ "¤": 98,
+ "¥": 99,
+ "¦": 100,
+ "§": 101,
+ "¨": 102,
+ "©": 103,
+ "ª": 104,
+ "«": 105,
+ "¬": 106,
+ "®": 107,
+ "¯": 108,
+ "°": 109,
+ "±": 110,
+ "²": 111,
+ "³": 112,
+ "´": 113,
+ "µ": 114,
+ "¶": 115,
+ "·": 116,
+ "¸": 117,
+ "¹": 118,
+ "º": 119,
+ "»": 120,
+ "¼": 121,
+ "½": 122,
+ "¾": 123,
+ "¿": 124,
+ "À": 125,
+ "Á": 126,
+ "Â": 127,
+ "Ã": 128,
+ "Ä": 129,
+ "Å": 130,
+ "Æ": 131,
+ "Ç": 132,
+ "È": 133,
+ "É": 134,
+ "Ê": 135,
+ "Ë": 136,
+ "Ì": 137,
+ "Í": 138,
+ "Î": 139,
+ "Ï": 140,
+ "Ð": 141,
+ "Ñ": 142,
+ "Ò": 143,
+ "Ó": 144,
+ "Ô": 145,
+ "Õ": 146,
+ "Ö": 147,
+ "×": 148,
+ "Ø": 149,
+ "Ù": 150,
+ "Ú": 151,
+ "Û": 152,
+ "Ü": 153,
+ "Ý": 154,
+ "Þ": 155,
+ "ß": 156,
+ "à": 157,
+ "á": 158,
+ "â": 159,
+ "ã": 160,
+ "ä": 161,
+ "å": 162,
+ "æ": 163,
+ "ç": 164,
+ "è": 165,
+ "é": 166,
+ "ê": 167,
+ "ë": 168,
+ "ì": 169,
+ "í": 170,
+ "î": 171,
+ "ï": 172,
+ "ð": 173,
+ "ñ": 174,
+ "ò": 175,
+ "ó": 176,
+ "ô": 177,
+ "õ": 178,
+ "ö": 179,
+ "÷": 180,
+ "ø": 181,
+ "ù": 182,
+ "ú": 183,
+ "û": 184,
+ "ü": 185,
+ "ý": 186,
+ "þ": 187,
+ "ÿ": 188,
+ "Ā": 189,
+ "ā": 190,
+ "Ă": 191,
+ "ă": 192,
+ "Ą": 193,
+ "ą": 194,
+ "Ć": 195,
+ "ć": 196,
+ "Ĉ": 197,
+ "ĉ": 198,
+ "Ċ": 199,
+ "ċ": 200,
+ "Č": 201,
+ "č": 202,
+ "Ď": 203,
+ "ď": 204,
+ "Đ": 205,
+ "đ": 206,
+ "Ē": 207,
+ "ē": 208,
+ "Ĕ": 209,
+ "ĕ": 210,
+ "Ė": 211,
+ "ė": 212,
+ "Ę": 213,
+ "ę": 214,
+ "Ě": 215,
+ "ě": 216,
+ "Ĝ": 217,
+ "ĝ": 218,
+ "Ğ": 219,
+ "ğ": 220,
+ "Ġ": 221,
+ "ġ": 222,
+ "Ģ": 223,
+ "ģ": 224,
+ "Ĥ": 225,
+ "ĥ": 226,
+ "Ħ": 227,
+ "ħ": 228,
+ "Ĩ": 229,
+ "ĩ": 230,
+ "Ī": 231,
+ "ī": 232,
+ "Ĭ": 233,
+ "ĭ": 234,
+ "Į": 235,
+ "į": 236,
+ "İ": 237,
+ "ı": 238,
+ "IJ": 239,
+ "ij": 240,
+ "Ĵ": 241,
+ "ĵ": 242,
+ "Ķ": 243,
+ "ķ": 244,
+ "ĸ": 245,
+ "Ĺ": 246,
+ "ĺ": 247,
+ "Ļ": 248,
+ "ļ": 249,
+ "Ľ": 250,
+ "ľ": 251,
+ "Ŀ": 252,
+ "ŀ": 253,
+ "Ł": 254,
+ "ł": 255,
+ "Ń": 256
+ },
+ "merges": []
+ }
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 1024,
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<|endoftext|>"
+}

vocab.json

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