tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "50256": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50257": {
      "content": "[DNA_A]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50258": {
      "content": "[DNA_C]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50259": {
      "content": "[DNA_G]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50260": {
      "content": "[DNA_T]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50261": {
      "content": "[DNA_R]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50262": {
      "content": "[DNA_Y]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50263": {
      "content": "[DNA_S]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50264": {
      "content": "[DNA_W]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50265": {
      "content": "[DNA_K]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50266": {
      "content": "[DNA_M]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50267": {
      "content": "[DNA_B]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50268": {
      "content": "[DNA_D]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50269": {
      "content": "[DNA_H]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50270": {
      "content": "[DNA_V]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50271": {
      "content": "[DNA_N]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50272": {
      "content": "[PROT_A]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50273": {
      "content": "[PROT_C]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50274": {
      "content": "[PROT_D]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50275": {
      "content": "[PROT_E]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50276": {
      "content": "[PROT_F]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50277": {
      "content": "[PROT_G]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50278": {
      "content": "[PROT_H]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50279": {
      "content": "[PROT_I]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50280": {
      "content": "[PROT_K]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50281": {
      "content": "[PROT_L]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50282": {
      "content": "[PROT_M]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50283": {
      "content": "[PROT_N]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50284": {
      "content": "[PROT_P]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50285": {
      "content": "[PROT_Q]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50286": {
      "content": "[PROT_R]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50287": {
      "content": "[PROT_S]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50288": {
      "content": "[PROT_T]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50289": {
      "content": "[PROT_V]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50290": {
      "content": "[PROT_W]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50291": {
      "content": "[PROT_Y]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50292": {
      "content": "[PROT_*]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50293": {
      "content": "[PROT_X]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50294": {
      "content": "<|DNA|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50295": {
      "content": "<|ORGANISM|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50296": {
      "content": "<|PROTEIN|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50297": {
      "content": "<|END|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|DNA|>",
    "<|ORGANISM|>",
    "<|PROTEIN|>",
    "<|END|>"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "extra_special_tokens": {},
  "model_max_length": 1024,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}