tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<cls>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<eos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "95": {
      "content": "<archaea>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "96": {
      "content": "<bacteria>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "97": {
      "content": "<fungi>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "98": {
      "content": "<invertebrate>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "99": {
      "content": "<metagenomes>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100": {
      "content": "<plant>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "101": {
      "content": "<protozoa>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "102": {
      "content": "<vertebrate_mammalian>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "103": {
      "content": "<vertebrate_other>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "104": {
      "content": "<viral>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<archaea>",
    "<bacteria>",
    "<fungi>",
    "<invertebrate>",
    "<metagenomes>",
    "<plant>",
    "<protozoa>",
    "<vertebrate_mammalian>",
    "<vertebrate_other>",
    "<viral>"
  ],
  "clean_up_tokenization_spaces": true,
  "cls_token": "<cls>",
  "eos_token": "<eos>",
  "mask_token": "<mask>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "tokenizer_class": "EsmTokenizer",
  "unk_token": "<unk>"
}