tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_baichuan.BaichuanTokenizer",
      null
    ]
  },
  "bos_token": "<s>",
  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '</s>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '</s>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n' }}{% endif %}{% endfor %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "extra_special_tokens": {},
  "model_max_length": 4096,
  "pad_token": "<unk>",
  "padding_side": "left",
  "sp_model_kwargs": {},
  "split_special_tokens": false,
  "tokenizer_class": "BaichuanTokenizer",
  "unk_token": "<unk>",
  "use_fast": false
}