tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "50256": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50257": {
      "content": "[DRUG_START]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50258": {
      "content": "[DRUG_END]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50259": {
      "content": "[SIDE_EFFECTS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "[DRUG_START]",
    "[DRUG_END]",
    "[SIDE_EFFECTS]"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "max_length": 1024,
  "model_max_length": 1024,
  "pad_to_multiple_of": null,
  "pad_token": "<|endoftext|>",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "stride": 0,
  "tokenizer_class": "GPT2Tokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<|endoftext|>"
}