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
    },
    "49157": {
      "content": "<PAD>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49158": {
      "content": "<FUNC_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49159": {
      "content": "<INFO_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49160": {
      "content": "<CLS_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49161": {
      "content": "<AST_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49162": {
      "content": "<DESCRIPTION_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49163": {
      "content": "<COMMENTS_TOKEN>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<FUNC_TOKEN>",
    "<INFO_TOKEN>",
    "<CLS_TOKEN>",
    "<AST_TOKEN>",
    "<DESCRIPTION_TOKEN>",
    "<COMMENTS_TOKEN>"
  ],
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 2048,
  "pad_token": "<PAD>",
  "padding_side": "left",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}