tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32007": {
      "content": "▁<PRE>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32008": {
      "content": "▁<SUF>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32009": {
      "content": "▁<MID>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32010": {
      "content": "▁<EOT>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32016": {
      "content": "<human>:",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32017": {
      "content": "<bot>:",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32018": {
      "content": "<human_end>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32019": {
      "content": "<bot_end>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32020": {
      "content": "<func_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32021": {
      "content": "<func_end>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32022": {
      "content": "<docstring_start>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32023": {
      "content": "<docstring_end>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "▁<PRE>",
    "▁<MID>",
    "▁<SUF>",
    "▁<EOT>",
    "<human>:",
    "<bot>:",
    "<human_end>",
    "<bot_end>",
    "<func_start>",
    "<func_end>",
    "<docstring_start>",
    "<docstring_end>",
    "▁<PRE>",
    "▁<MID>",
    "▁<SUF>",
    "▁<EOT>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "eot_token": "▁<EOT>",
  "fill_token": "<FILL_ME>",
  "legacy": false,
  "middle_token": "▁<MID>",
  "model_max_length": 8192,
  "pad_token": "</s>",
  "prefix_token": "▁<PRE>",
  "sp_model_kwargs": {},
  "suffix_token": "▁<SUF>",
  "tokenizer_class": "CodeLlamaTokenizer",
  "truncation_side": "left",
  "unk_token": "<unk>",
  "use_default_system_prompt": false
}