tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": true,
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "50256": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50257": {
      "content": "<cluster_3>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50258": {
      "content": "<cluster_1>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50259": {
      "content": "<cluster_0>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50260": {
      "content": "<cluster_4>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "50261": {
      "content": "<cluster_2>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "extra_special_tokens": {},
  "model_max_length": 2048,
  "pad_token": "<|endoftext|>",
  "padding_side": "right",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}