tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "add_prefix_space": null,
  "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
    },
    "32000": {
      "content": "<instruction>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32001": {
      "content": "</instruction>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<instruction>",
    "</instruction>"
  ],
  "bos_token": "<s>",
  "bos_token_id": 1,
  "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<instruction>' + message['content'].strip() + '</instruction>'}}{% elif message['role'] == 'assistant' %}{{ message['content'].strip() + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "eos_token_id": 2,
  "legacy": false,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "pad_token_id": 3,
  "padding_side": "right",
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": "<unk>",
  "unk_token_id": 0,
  "use_default_system_prompt": false
}