tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<|plamo:unk|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|plamo:bos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|plamo:eos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|plamo:pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_plamo.Plamo2Tokenizer",
      null
    ]
  },
  "bos_token": "<|plamo:bos|>",
  "clean_up_tokenization_spaces": false,
  "cls_token": null,
  "eos_token": "<|plamo:bos|>",
  "extra_special_tokens": {},
  "local_file_only": true,
  "mask_token": null,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|plamo:pad|>",
  "sep_token": null,
  "tokenizer_class": "Plamo2Tokenizer",
  "unk_token": "<|plamo:unk|>",
  "chat_template": "{{- \"<|plamo:op|>dataset\\ntranslation\\n\" -}}\n{% for message in messages %}\n    {%- if message['role'] == 'user' %}\n        {{- '<|plamo:op|>input lang=Japanese|English\\n' + message['content'] + '\\n' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- '<|plamo:op|>output\\n' + message['content']}}\n        {%- if not loop.last %}\n            {{- '\\n'}}\n        {%- endif %}\n    {%- endif %}\n    {% if loop.last and message['role'] != 'assistant' and add_generation_prompt %}\n        {{- '<|plamo:op|>output\\n' -}}\n    {% endif %}\n{% endfor %}\n"
}