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": "<TITLE>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50258": {
      "content": "</TITLE>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50259": {
      "content": "<CHANNEL>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50260": {
      "content": "</CHANNEL>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50261": {
      "content": "<CATEGORY>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50262": {
      "content": "</CATEGORY>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50263": {
      "content": "<TAGS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50264": {
      "content": "</TAGS>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50265": {
      "content": "<COMMENT>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50266": {
      "content": "</COMMENT>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<TITLE>",
    "</TITLE>",
    "<CHANNEL>",
    "</CHANNEL>",
    "<CATEGORY>",
    "</CATEGORY>",
    "<TAGS>",
    "</TAGS>",
    "<COMMENT>",
    "</COMMENT>"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "model_max_length": 1024,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}