tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "49152": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49153": {
      "content": "<fim-prefix>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49154": {
      "content": "<fim-middle>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49155": {
      "content": "<fim-suffix>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49156": {
      "content": "<fim-pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|endoftext|>",
    "<fim-prefix>",
    "<fim-middle>",
    "<fim-suffix>",
    "<fim-pad>"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 2048,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}