tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "75": {
      "content": "<|startoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "76": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "77": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "78": {
      "content": "<|mdm_mask|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "79": {
      "content": "<role>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "80": {
      "content": "</role>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "81": {
      "content": "<|arithmetic_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "82": {
      "content": "<|arithmetic_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "83": {
      "content": "<|number_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "84": {
      "content": "<|number_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|mdm_mask|>",
    "<role>",
    "</role>",
    "<|arithmetic_start|>",
    "<|arithmetic_end|>",
    "<|number_start|>",
    "<|number_end|>"
  ],
  "bos_token": "<|startoftext|>",
  "clean_up_tokenization_spaces": false,
  "cls_token": "[CLS]",
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "fast_tokenizer": true,
  "gmask_token": "[gMASK]",
  "mask_token": "<|mdm_mask|>",
  "merges_file": null,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|endoftext|>",
  "padding_side": "right",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "trust_remote_code": true
}