tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32000": {
      "content": "<|fim_prefix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "<|fim_middle|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "<|fim_suffix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "<|fim_pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "<|filename|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32005": {
      "content": "<|gh_stars|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32006": {
      "content": "<|issue_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32007": {
      "content": "<|issue_comment|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32008": {
      "content": "<|issue_closed|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32009": {
      "content": "<|jupyter_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32010": {
      "content": "<|jupyter_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32011": {
      "content": "<|jupyter_code|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32012": {
      "content": "<|jupyter_output|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32013": {
      "content": "<|empty_output|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32014": {
      "content": "<|commit_before|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32015": {
      "content": "<|commit_msg|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32016": {
      "content": "<|commit_after|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32017": {
      "content": "<|reponame|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32018": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32019": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32020": {
      "content": "<|sys_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32021": {
      "content": "<|sys_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<unk>",
    "<s>",
    "</s>",
    "<|fim_prefix|>",
    "<|fim_middle|>",
    "<|fim_suffix|>",
    "<|fim_pad|>",
    "<|filename|>",
    "<|gh_stars|>",
    "<|issue_start|>",
    "<|issue_comment|>",
    "<|issue_closed|>",
    "<|jupyter_start|>",
    "<|jupyter_text|>",
    "<|jupyter_code|>",
    "<|jupyter_output|>",
    "<|empty_output|>",
    "<|commit_before|>",
    "<|commit_msg|>",
    "<|commit_after|>",
    "<|reponame|>",
    "<|im_start|>",
    "<|im_end|>",
    "<|sys_start|>",
    "<|sys_end|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      null,
      "tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
    ]
  },
  "bos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "legacy": false,
  "model_max_length": 2048,
  "pad_token": null,
  "padding_side": "right",
  "sp_model_kwargs": {},
  "tokenizer_class": "CrystalCoderTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": false,
    "rstrip": false,
    "single_word": false
  },
  "use_default_system_prompt": false
}