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]

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,553 @@
+{
+ "version": "1.0",
+ "truncation": null,
+ "padding": null,
+ "added_tokens": [
+ {
+ "id": 0,
+ "content": "<|endoftext|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "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": true,
+ "use_regex": true
+ },
+ "decoder": null,
+ "model": {
+ "type": "BPE",
+ "dropout": null,
+ "unk_token": "<|endoftext|>",
+ "continuing_subword_prefix": null,
+ "end_of_word_suffix": null,
+ "fuse_unk": false,
+ "byte_fallback": false,
+ "ignore_merges": false,
+ "vocab": {
+ "<|endoftext|>": 0,
+ "\u0000": 1,
+ "\u0001": 2,
+ "\u0002": 3,
+ "\u0003": 4,
+ "\u0004": 5,
+ "\u0005": 6,
+ "\u0006": 7,
+ "\u0007": 8,
+ "\b": 9,
+ "\t": 10,
+ "\n": 11,
+ "\u000b": 12,
+ "\f": 13,
+ "\r": 14,
+ "\u000e": 15,
+ "\u000f": 16,
+ "\u0010": 17,
+ "\u0011": 18,
+ "\u0012": 19,
+ "\u0013": 20,
+ "\u0014": 21,
+ "\u0015": 22,
+ "\u0016": 23,
+ "\u0017": 24,
+ "\u0018": 25,
+ "\u0019": 26,
+ "\u001a": 27,
+ "\u001b": 28,
+ "\u001c": 29,
+ "\u001d": 30,
+ "\u001e": 31,
+ "\u001f": 32,
+ " ": 33,
+ "!": 34,
+ "\"": 35,
+ "#": 36,
+ "$": 37,
+ "%": 38,
+ "&": 39,
+ "'": 40,
+ "(": 41,
+ ")": 42,
+ "*": 43,
+ "+": 44,
+ ",": 45,
+ "-": 46,
+ ".": 47,
+ "/": 48,
+ "0": 49,
+ "1": 50,
+ "2": 51,
+ "3": 52,
+ "4": 53,
+ "5": 54,
+ "6": 55,
+ "7": 56,
+ "8": 57,
+ "9": 58,
+ ":": 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,
+ "a": 98,
+ "b": 99,
+ "c": 100,
+ "d": 101,
+ "e": 102,
+ "f": 103,
+ "g": 104,
+ "h": 105,
+ "i": 106,
+ "j": 107,
+ "k": 108,
+ "l": 109,
+ "m": 110,
+ "n": 111,
+ "o": 112,
+ "p": 113,
+ "q": 114,
+ "r": 115,
+ "s": 116,
+ "t": 117,
+ "u": 118,
+ "v": 119,
+ "w": 120,
+ "x": 121,
+ "y": 122,
+ "z": 123,
+ "{": 124,
+ "|": 125,
+ "}": 126,
+ "~": 127,
+ "": 128,
+ "€": 129,
+ "": 130,
+ "‚": 131,
+ "ƒ": 132,
+ "„": 133,
+ "…": 134,
+ "†": 135,
+ "‡": 136,
+ "ˆ": 137,
+ "‰": 138,
+ "Š": 139,
+ "‹": 140,
+ "Œ": 141,
+ "": 142,
+ "Ž": 143,
+ "": 144,
+ "": 145,
+ "‘": 146,
+ "’": 147,
+ "“": 148,
+ "”": 149,
+ "•": 150,
+ "–": 151,
+ "—": 152,
+ "˜": 153,
+ "™": 154,
+ "š": 155,
+ "›": 156,
+ "œ": 157,
+ "": 158,
+ "ž": 159,
+ "Ÿ": 160,
+ " ": 161,
+ "¡": 162,
+ "¢": 163,
+ "£": 164,
+ "¤": 165,
+ "¥": 166,
+ "¦": 167,
+ "§": 168,
+ "¨": 169,
+ "©": 170,
+ "ª": 171,
+ "«": 172,
+ "¬": 173,
+ "­": 174,
+ "®": 175,
+ "¯": 176,
+ "°": 177,
+ "±": 178,
+ "²": 179,
+ "³": 180,
+ "´": 181,
+ "µ": 182,
+ "¶": 183,
+ "·": 184,
+ "¸": 185,
+ "¹": 186,
+ "º": 187,
+ "»": 188,
+ "¼": 189,
+ "½": 190,
+ "¾": 191,
+ "¿": 192,
+ "À": 193,
+ "Á": 194,
+ "Â": 195,
+ "Ã": 196,
+ "Ä": 197,
+ "Å": 198,
+ "Æ": 199,
+ "Ç": 200,
+ "È": 201,
+ "É": 202,
+ "Ê": 203,
+ "Ë": 204,
+ "Ì": 205,
+ "Í": 206,
+ "Î": 207,
+ "Ï": 208,
+ "Ð": 209,
+ "Ñ": 210,
+ "Ò": 211,
+ "Ó": 212,
+ "Ô": 213,
+ "Õ": 214,
+ "Ö": 215,
+ "×": 216,
+ "Ø": 217,
+ "Ù": 218,
+ "Ú": 219,
+ "Û": 220,
+ "Ü": 221,
+ "Ý": 222,
+ "Þ": 223,
+ "ß": 224,
+ "à": 225,
+ "á": 226,
+ "â": 227,
+ "ã": 228,
+ "ä": 229,
+ "å": 230,
+ "æ": 231,
+ "ç": 232,
+ "è": 233,
+ "é": 234,
+ "ê": 235,
+ "ë": 236,
+ "ì": 237,
+ "í": 238,
+ "î": 239,
+ "ï": 240,
+ "ð": 241,
+ "ñ": 242,
+ "ò": 243,
+ "ó": 244,
+ "ô": 245,
+ "õ": 246,
+ "ö": 247,
+ "÷": 248,
+ "ø": 249,
+ "ù": 250,
+ "ú": 251,
+ "û": 252,
+ "ü": 253,
+ "ý": 254,
+ "þ": 255,
+ "ÿ": 256,
+ "Ċ": 257,
+ "Ġ": 258,
+ "Ġt": 259,
+ "he": 260,
+ "Ġa": 261,
+ "Ġs": 262,
+ "nd": 263,
+ "Ġw": 264,
+ "Ġthe": 265,
+ "ed": 266,
+ "Ġb": 267,
+ "Ġto": 268,
+ "Ġand": 269,
+ "Ġh": 270,
+ "Ġf": 271,
+ "ĠT": 272,
+ "in": 273,
+ "Ġwa": 274,
+ "re": 275,
+ "it": 276,
+ "ou": 277,
+ "Ġl": 278,
+ "Ġd": 279,
+ "Ġc": 280,
+ "Ġp": 281,
+ "ay": 282,
+ "Ġm": 283,
+ "er": 284,
+ "Ġwas": 285,
+ "ĠThe": 286,
+ "om": 287,
+ "Ġhe": 288,
+ "is": 289,
+ "Ġn": 290,
+ "ar": 291,
+ "im": 292,
+ "on": 293,
+ "Ġsa": 294,
+ "id": 295,
+ "ll": 296,
+ "Ġha": 297,
+ "Ġg": 298,
+ "at": 299,
+ "ĠS": 300,
+ "ing": 301,
+ "ot": 302,
+ "en": 303,
+ "an": 304,
+ "le": 305,
+ "or": 306,
+ "end": 307,
+ "ir": 308,
+ "of": 309,
+ "am": 310,
+ "et": 311,
+ "ĠH": 312,
+ "Ġit": 313,
+ "Ġth": 314,
+ "ig": 315,
+ "ĠThey": 316,
+ "Ġin": 317,
+ "il": 318,
+ "Ġpl": 319,
+ "Ġ\"": 320,
+ "ĠHe": 321,
+ "ow": 322,
+ "ri": 323,
+ "ver": 324,
+ "ut": 325,
+ "Ġu": 326,
+ "Ġbe": 327,
+ "Ġplay": 328,
+ "Ġsaid": 329,
+ "ith": 330,
+ "Ġday": 331,
+ "Ġwith": 332,
+ "pp": 333,
+ "On": 334,
+ "Ġy": 335,
+ "oo": 336,
+ "ked": 337,
+ "Ġr": 338,
+ "ex": 339,
+ "Ġher": 340,
+ "ce": 341,
+ "ĠI": 342,
+ "ĠTim": 343,
+ "ĠShe": 344,
+ "ld": 345,
+ "Ġhis": 346,
+ "Ġst": 347,
+ "ke": 348,
+ "Ġbig": 349,
+ "nt": 350,
+ "ck": 351,
+ "very": 352,
+ "Ġyou": 353,
+ "st": 354,
+ "ve": 355,
+ "Ġhapp": 356,
+ "un": 357,
+ "Ġon": 358,
+ "riend": 359,
+ "Ġfriend": 360,
+ "all": 361,
+ "ily": 362,
+ "ext": 363,
+ "ĠL": 364,
+ "Ġthey": 365,
+ "oft": 366,
+ "Ġwe": 367,
+ "Ġhad": 368,
+ "Ġnot": 369,
+ "Ġli": 370,
+ "Ġup": 371,
+ "her": 372,
+ "Ġwant": 373,
+ "Ġof": 374,
+ "itt": 375,
+ "<|": 376,
+ "|>": 377,
+ "endoft": 378,
+ "endoftext": 379,
+ "ad": 380,
+ "se": 381,
+ "ĠB": 382,
+ "Ġdo": 383
+ },
+ "merges": [
+ "Ġ t",
+ "h e",
+ "Ġ a",
+ "Ġ s",
+ "n d",
+ "Ġ w",
+ "Ġt he",
+ "e d",
+ "Ġ b",
+ "Ġt o",
+ "Ġa nd",
+ "Ġ h",
+ "Ġ f",
+ "Ġ T",
+ "i n",
+ "Ġw a",
+ "r e",
+ "i t",
+ "o u",
+ "Ġ l",
+ "Ġ d",
+ "Ġ c",
+ "Ġ p",
+ "a y",
+ "Ġ m",
+ "e r",
+ "Ġwa s",
+ "ĠT he",
+ "o m",
+ "Ġ he",
+ "i s",
+ "Ġ n",
+ "a r",
+ "i m",
+ "o n",
+ "Ġs a",
+ "i d",
+ "l l",
+ "Ġh a",
+ "Ġ g",
+ "a t",
+ "Ġ S",
+ "in g",
+ "o t",
+ "e n",
+ "a n",
+ "l e",
+ "o r",
+ "e nd",
+ "i r",
+ "o f",
+ "a m",
+ "e t",
+ "Ġ H",
+ "Ġ it",
+ "Ġt h",
+ "i g",
+ "ĠThe y",
+ "Ġ in",
+ "i l",
+ "Ġp l",
+ "Ġ \"",
+ "ĠH e",
+ "o w",
+ "r i",
+ "v er",
+ "u t",
+ "Ġ u",
+ "Ġb e",
+ "Ġpl ay",
+ "Ġsa id",
+ "it h",
+ "Ġd ay",
+ "Ġw ith",
+ "p p",
+ "O n",
+ "Ġ y",
+ "o o",
+ "k ed",
+ "Ġ r",
+ "e x",
+ "Ġhe r",
+ "c e",
+ "Ġ I",
+ "ĠT im",
+ "ĠS he",
+ "l d",
+ "Ġh is",
+ "Ġs t",
+ "k e",
+ "Ġb ig",
+ "n t",
+ "c k",
+ "ver y",
+ "Ġy ou",
+ "s t",
+ "v e",
+ "Ġha pp",
+ "u n",
+ "Ġ on",
+ "ri end",
+ "Ġf riend",
+ "a ll",
+ "il y",
+ "ex t",
+ "Ġ L",
+ "Ġthe y",
+ "of t",
+ "Ġw e",
+ "Ġha d",
+ "Ġn ot",
+ "Ġl i",
+ "Ġu p",
+ "he r",
+ "Ġwa nt",
+ "Ġ of",
+ "it t",
+ "< |",
+ "| >",
+ "end oft",
+ "endoft ext",
+ "a d",
+ "s e",
+ "Ġ B",
+ "Ġd o"
+ ]
+ }
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 1000000000000000019884624838656,
+ "tokenizer_class": "PreTrainedTokenizerFast",
+ "unk_token": "<|endoftext|>"
+}