tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "32000": {
      "content": "õ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32001": {
      "content": "÷",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32002": {
      "content": "Á",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32003": {
      "content": "ý",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32004": {
      "content": "À",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32005": {
      "content": "ÿ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32006": {
      "content": "ø",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32007": {
      "content": "ú",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32008": {
      "content": "þ",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32009": {
      "content": "ü",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32010": {
      "content": "ù",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32011": {
      "content": "ö",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32012": {
      "content": "û",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32013": {
      "content": "<｜begin▁of▁sentence｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32014": {
      "content": "<｜end▁of▁sentence｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32015": {
      "content": "<｜fim▁hole｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32016": {
      "content": "<｜fim▁begin｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32017": {
      "content": "<｜fim▁end｜>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32018": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32019": {
      "content": "<|User|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32020": {
      "content": "<|Assistant|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32021": {
      "content": "<|EOT|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "32022": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32023": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32024": {
      "content": "<|text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32025": {
      "content": "<|code|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32026": {
      "content": "<|execution|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32027": {
      "content": "<|endofblock|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32028": {
      "content": "<|endofmessage|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|user|>",
    "<|assistant|>",
    "<|text|>",
    "<|code|>",
    "<|execution|>",
    "<|endofblock|>",
    "<|endofmessage|>"
  ],
  "bos_token": "<｜begin▁of▁sentence｜>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<｜end▁of▁sentence｜>",
  "legacy": true,
  "model_max_length": 16384,
  "pad_token": "<｜end▁of▁sentence｜>",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": null,
  "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 %}"
}