tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "add_prefix_space": true,
  "added_tokens_decoder": {
    "0": {
      "content": "<oov>",
      "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
    }
  },
  "auto_map": {
    "AutoTokenizer": [
      "tokenizer.DNAKmerTokenizer",
      null
    ]
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "extra_special_tokens": {},
  "kmer": 6,
  "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "sp_model_kwargs": {},
  "spaces_between_special_tokens": false,
  "tokenizer_class": "DNAKmerTokenizer",
  "unk_token": "<oov>",
  "use_default_system_prompt": false,
  "use_fast": false,
  "k": 6,
  "chat_template": "<s>{% for message in messages %}{% if message.role == 'user' %}<bog>{{ 'A' * ((6 - message.content|length % 6) % 6) }}{{ message.content | trim }}</s>{% elif message.role == 'assistant' %}<bok>{{ 'A' * ((6 - message.content|length % 6) % 6) }}{{ message.content | trim }}</s>{% endif %}{% endfor %}{% if add_generation_prompt %}<bok>{% endif %}"
}