tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|bos|>",
      "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
    },
    "30": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "31": {
      "content": "<SMILES>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32": {
      "content": "</SMILES>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "33": {
      "content": "<SEQ>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "34": {
      "content": "</SEQ>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "35": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<SMILES>",
    "</SMILES>",
    "<SEQ>",
    "</SEQ>"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "max_length": 512,
  "model_max_length": 1000000000000000019884624838656,
  "pad_to_multiple_of": null,
  "pad_token": "[PAD]",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "stride": 0,
  "tokenizer_class": "GPT2Tokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<|endoftext|>"
}