tokenizer_config.json

{
  "add_bos_token": false,
  "add_dummy_prefix_space": false,
  "add_eos_token": false,
  "add_prefix_space": 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
    },
    "3": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<sep>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<cls>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "8": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "9": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "10": {
      "content": "<|available_tools|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "11": {
      "content": "<|tool_calls|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "12": {
      "content": "<|tool_results|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "13": {
      "content": "<|code|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "14": {
      "content": "<|file|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "102397": {
      "content": "<|prefix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "102398": {
      "content": "<|suffix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "102399": {
      "content": "<|middle|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<cls>",
  "do_lower_case": false,
  "eos_token": "</s>",
  "extra_ids": 0,
  "extra_special_tokens": {},
  "keep_accents": true,
  "legacy": false,
  "mask_token": "<mask>",
  "model_max_length": 8192,
  "pad_token": "<pad>",
  "padding_side": "left",
  "sep_token": "<sep>",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "use_default_system_prompt": false,
  "chat_template": "\n{%- set system_messages = messages | selectattr('role', 'equalto', 'system') | list -%}\n{%- set target = 'Japanese' -%}\n{%- if system_messages and (system_messages | length > 0) -%}\n    {%- set target = (system_messages[-1].get('content', '') | trim) -%}\n{%- endif -%}\n\n{{- '<|system|>' + 'You are a translator. You will translate input into ' + target + '.' + eos_token -}}\n\n{%- for message in messages -%}\n    {%- if message['role'] == 'user' -%}\n        {{- '<|user|>' + message.get('content', '') + eos_token -}}\n    {%- elif message['role'] == 'assistant' -%}\n        {{- '<|assistant|>' + message.get('content', '') + eos_token -}}\n    {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n{{- '<|assistant|>' -}}\n{%- endif -%}\n"
}