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 +1,3 @@
+{
+  "pad_token": "<|pad|>"
+}

tokenizer.json

@@ -0,0 +1,364 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|im_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<|start_bytes|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<|end_bytes|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "<|semantic|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": "<|pad|>",
+      "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": 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": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "<|im_start|>": 0,
+      "<|im_sep|>": 1,
+      "<|start_bytes|>": 2,
+      "<|end_bytes|>": 3,
+      "<|im_end|>": 4,
+      "<|semantic|>": 5,
+      "<|pad|>": 6,
+      "!": 7,
+      "\"": 8,
+      "#": 9,
+      "$": 10,
+      "%": 11,
+      "&": 12,
+      "'": 13,
+      "(": 14,
+      ")": 15,
+      "*": 16,
+      "+": 17,
+      ",": 18,
+      "-": 19,
+      ".": 20,
+      "/": 21,
+      "0": 22,
+      "1": 23,
+      "2": 24,
+      "3": 25,
+      "4": 26,
+      "5": 27,
+      "6": 28,
+      "7": 29,
+      "8": 30,
+      "9": 31,
+      ":": 32,
+      ";": 33,
+      "<": 34,
+      "=": 35,
+      ">": 36,
+      "?": 37,
+      "@": 38,
+      "A": 39,
+      "B": 40,
+      "C": 41,
+      "D": 42,
+      "E": 43,
+      "F": 44,
+      "G": 45,
+      "H": 46,
+      "I": 47,
+      "J": 48,
+      "K": 49,
+      "L": 50,
+      "M": 51,
+      "N": 52,
+      "O": 53,
+      "P": 54,
+      "Q": 55,
+      "R": 56,
+      "S": 57,
+      "T": 58,
+      "U": 59,
+      "V": 60,
+      "W": 61,
+      "X": 62,
+      "Y": 63,
+      "Z": 64,
+      "[": 65,
+      "\\": 66,
+      "]": 67,
+      "^": 68,
+      "_": 69,
+      "`": 70,
+      "a": 71,
+      "b": 72,
+      "c": 73,
+      "d": 74,
+      "e": 75,
+      "f": 76,
+      "g": 77,
+      "h": 78,
+      "i": 79,
+      "j": 80,
+      "k": 81,
+      "l": 82,
+      "m": 83,
+      "n": 84,
+      "o": 85,
+      "p": 86,
+      "q": 87,
+      "r": 88,
+      "s": 89,
+      "t": 90,
+      "u": 91,
+      "v": 92,
+      "w": 93,
+      "x": 94,
+      "y": 95,
+      "z": 96,
+      "{": 97,
+      "|": 98,
+      "}": 99,
+      "~": 100,
+      "¡": 101,
+      "¢": 102,
+      "£": 103,
+      "¤": 104,
+      "¥": 105,
+      "¦": 106,
+      "§": 107,
+      "¨": 108,
+      "©": 109,
+      "ª": 110,
+      "«": 111,
+      "¬": 112,
+      "®": 113,
+      "¯": 114,
+      "°": 115,
+      "±": 116,
+      "²": 117,
+      "³": 118,
+      "´": 119,
+      "µ": 120,
+      "¶": 121,
+      "·": 122,
+      "¸": 123,
+      "¹": 124,
+      "º": 125,
+      "»": 126,
+      "¼": 127,
+      "½": 128,
+      "¾": 129,
+      "¿": 130,
+      "À": 131,
+      "Á": 132,
+      "Â": 133,
+      "Ã": 134,
+      "Ä": 135,
+      "Å": 136,
+      "Æ": 137,
+      "Ç": 138,
+      "È": 139,
+      "É": 140,
+      "Ê": 141,
+      "Ë": 142,
+      "Ì": 143,
+      "Í": 144,
+      "Î": 145,
+      "Ï": 146,
+      "Ð": 147,
+      "Ñ": 148,
+      "Ò": 149,
+      "Ó": 150,
+      "Ô": 151,
+      "Õ": 152,
+      "Ö": 153,
+      "×": 154,
+      "Ø": 155,
+      "Ù": 156,
+      "Ú": 157,
+      "Û": 158,
+      "Ü": 159,
+      "Ý": 160,
+      "Þ": 161,
+      "ß": 162,
+      "à": 163,
+      "á": 164,
+      "â": 165,
+      "ã": 166,
+      "ä": 167,
+      "å": 168,
+      "æ": 169,
+      "ç": 170,
+      "è": 171,
+      "é": 172,
+      "ê": 173,
+      "ë": 174,
+      "ì": 175,
+      "í": 176,
+      "î": 177,
+      "ï": 178,
+      "ð": 179,
+      "ñ": 180,
+      "ò": 181,
+      "ó": 182,
+      "ô": 183,
+      "õ": 184,
+      "ö": 185,
+      "÷": 186,
+      "ø": 187,
+      "ù": 188,
+      "ú": 189,
+      "û": 190,
+      "ü": 191,
+      "ý": 192,
+      "þ": 193,
+      "ÿ": 194,
+      "Ā": 195,
+      "ā": 196,
+      "Ă": 197,
+      "ă": 198,
+      "Ą": 199,
+      "ą": 200,
+      "Ć": 201,
+      "ć": 202,
+      "Ĉ": 203,
+      "ĉ": 204,
+      "Ċ": 205,
+      "ċ": 206,
+      "Č": 207,
+      "č": 208,
+      "Ď": 209,
+      "ď": 210,
+      "Đ": 211,
+      "đ": 212,
+      "Ē": 213,
+      "ē": 214,
+      "Ĕ": 215,
+      "ĕ": 216,
+      "Ė": 217,
+      "ė": 218,
+      "Ę": 219,
+      "ę": 220,
+      "Ě": 221,
+      "ě": 222,
+      "Ĝ": 223,
+      "ĝ": 224,
+      "Ğ": 225,
+      "ğ": 226,
+      "Ġ": 227,
+      "ġ": 228,
+      "Ģ": 229,
+      "ģ": 230,
+      "Ĥ": 231,
+      "ĥ": 232,
+      "Ħ": 233,
+      "ħ": 234,
+      "Ĩ": 235,
+      "ĩ": 236,
+      "Ī": 237,
+      "ī": 238,
+      "Ĭ": 239,
+      "ĭ": 240,
+      "Į": 241,
+      "į": 242,
+      "İ": 243,
+      "ı": 244,
+      "IJ": 245,
+      "ij": 246,
+      "Ĵ": 247,
+      "ĵ": 248,
+      "Ķ": 249,
+      "ķ": 250,
+      "ĸ": 251,
+      "Ĺ": 252,
+      "ĺ": 253,
+      "Ļ": 254,
+      "ļ": 255,
+      "Ľ": 256,
+      "ľ": 257,
+      "Ŀ": 258,
+      "ŀ": 259,
+      "Ł": 260,
+      "ł": 261,
+      "Ń": 262
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|start_bytes|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|end_bytes|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|semantic|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}