tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "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": "▁<PRE>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "▁<MID>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32002": {
      "content": "▁<SUF>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32003": {
      "content": "▁<EOT>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32004": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32005": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32006": {
      "content": "<|text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32007": {
      "content": "<|code|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32008": {
      "content": "<|execution|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32009": {
      "content": "<|endofblock|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32010": {
      "content": "<|endofmessage|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "▁<PRE>",
    "▁<MID>",
    "▁<SUF>",
    "▁<EOT>",
    "<|user|>",
    "<|assistant|>",
    "<|text|>",
    "<|code|>",
    "<|execution|>",
    "<|endofblock|>",
    "<|endofmessage|>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "eot_token": "▁<EOT>",
  "fill_token": "<FILL_ME>",
  "legacy": null,
  "middle_token": "▁<MID>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "</s>",
  "prefix_token": "▁<PRE>",
  "sp_model_kwargs": {},
  "suffix_token": "▁<SUF>",
  "tokenizer_class": "CodeLlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false,
  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' }}{% elif message['role'] == 'system' %}{{ '<|system|>' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>' }}{% endif %}{% if message['content'] is string %}{{ '<|text|>' + message['content'] + '<|endofblock|>' }}{% elif message['content'] is sequence %}{% for block in message['content'] %}{% if block['type'] == 'text' %}{{ '<|text|>' }}{% elif block['type'] == 'code' %}{{ '<|code|>' }}{% elif block['type'] == 'execution' %}{{ '<|execution|>' }}{% endif %}{{ block['content'] + '<|endofblock|>' }}{% endfor %}{% endif %}{{ '<|endofmessage|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}"
}