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]
+
+

added_tokens.json

@@ -0,0 +1,122 @@
+{
+  "[PAD]": 6368,
+  "[UNK]": 6367,
+  "ã": 6398,
+  "ãː": 6400,
+  "ãˤ": 6408,
+  "ã̰": 6460,
+  "ẽ": 6374,
+  "ẽː": 6375,
+  "ẽˤ": 6409,
+  "ḛ̃": 6448,
+  "h̩": 6483,
+  "ĩ": 6425,
+  "ĩː": 6426,
+  "ĩˤ": 6441,
+  "ḭ̃": 6465,
+  "l̩": 6485,
+  "l̪̩": 6486,
+  "õ": 6394,
+  "õː": 6396,
+  "õˤ": 6416,
+  "õ̰": 6458,
+  "r̩": 6473,
+  "r̪̩": 6475,
+  "ũ": 6437,
+  "ũː": 6438,
+  "ũˤ": 6445,
+  "ṵ̃": 6471,
+  "ṳˤ": 6371,
+  "ỹ": 6435,
+  "ỹː": 6436,
+  "ỹˤ": 6446,
+  "ỹ̰": 6470,
+  "y̤ˤ": 6370,
+  "æ̃": 6399,
+  "æ̃ː": 6401,
+  "æ̃ˤ": 6410,
+  "æ̰̃": 6461,
+  "ø̃": 6378,
+  "ø̃ː": 6379,
+  "ø̃ˤ": 6417,
+  "ø̰̃": 6450,
+  "œ̃": 6376,
+  "œ̃ː": 6377,
+  "œ̃ˤ": 6413,
+  "œ̰̃": 6449,
+  "ɐ̃": 6385,
+  "ɐ̃ː": 6388,
+  "ɐ̃ˤ": 6407,
+  "ɐ̰̃": 6454,
+  "ɒ̃": 6421,
+  "ɒ̃ː": 6422,
+  "ɒ̃ˤ": 6418,
+  "ɒ̰̃": 6463,
+  "ɔ̃": 6390,
+  "ɔ̃ː": 6392,
+  "ɔ̃ˤ": 6414,
+  "ɔ̰̃": 6456,
+  "ɘ̃": 6381,
+  "ɘ̃ː": 6383,
+  "ɘ̃ˤ": 6405,
+  "ɘ̰̃": 6452,
+  "ə̃": 6380,
+  "ə̃ː": 6382,
+  "ə̃ˤ": 6404,
+  "ə̰̃": 6451,
+  "ɛ̃": 6372,
+  "ɛ̃ː": 6373,
+  "ɛ̃ˤ": 6406,
+  "ɛ̰̃": 6447,
+  "ɜ̃": 6384,
+  "ɜ̃ː": 6387,
+  "ɜ̃ˤ": 6411,
+  "ɜ̰̃": 6453,
+  "ɞ̃": 6395,
+  "ɞ̃ː": 6397,
+  "ɞ̃ˤ": 6419,
+  "ɞ̰̃": 6459,
+  "ɦ̩": 6484,
+  "ɨ̃": 6431,
+  "ɨ̃ː": 6432,
+  "ɨ̃ˤ": 6442,
+  "ɨ̰̃": 6468,
+  "ɪ̃": 6423,
+  "ɪ̃ː": 6424,
+  "ɪ̃ˤ": 6439,
+  "ɪ̰̃": 6464,
+  "ɫ̩": 6480,
+  "ɭ̩": 6478,
+  "ɯ̃": 6429,
+  "ɯ̃ː": 6430,
+  "ɯ̃ˤ": 6440,
+  "ɯ̰̃": 6467,
+  "ɵ̃": 6391,
+  "ɵ̃ː": 6393,
+  "ɵ̃ˤ": 6415,
+  "ɵ̰̃": 6457,
+  "ɶ̃": 6402,
+  "ɶ̃ː": 6403,
+  "ɶ̃ˤ": 6420,
+  "ɶ̰̃": 6462,
+  "ɶ̤ˠ": 6369,
+  "ɺ̩": 6479,
+  "ɽ̩": 6472,
+  "ɾ̩": 6474,
+  "ʀ̩": 6477,
+  "ʊ̃": 6433,
+  "ʊ̃ː": 6434,
+  "ʊ̃ˤ": 6443,
+  "ʊ̰̃": 6469,
+  "ʌ̃": 6386,
+  "ʌ̃ː": 6389,
+  "ʌ̃ˤ": 6412,
+  "ʌ̰̃": 6455,
+  "ʎ̩": 6482,
+  "ʏ̃": 6427,
+  "ʏ̃ː": 6428,
+  "ʏ̃ˤ": 6444,
+  "ʏ̰̃": 6466,
+  "ʙ̩": 6476,
+  "ʟ̩": 6481
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}