tokenizer_config.json

{
    "add_bos_token": true,
    "add_eos_token": false,
    "added_tokens_decoder": {
      "0": {
        "content": "<PAD>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "1": {
        "content": "<UNK>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "2": {
        "content": "<CLS>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "3": {
        "content": "<SEP>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "4": {
        "content": "<MASK_TOKEN>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "5": {
        "content": "<s>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "6": {
        "content": "</s>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "7": {
        "content": "<EOP_TOKEN>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "255000": {
        "content": "<|im_start|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255001": {
        "content": "<|im_end|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255002": {
        "content": "<|YES_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255003": {
        "content": "<|NO_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255004": {
        "content": "<|GOOD_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255005": {
        "content": "<|BAD_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255006": {
        "content": "<|USER_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255007": {
        "content": "<|CHATBOT_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255008": {
        "content": "<|SYSTEM_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255009": {
        "content": "<|USER_0_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255010": {
        "content": "<|USER_1_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255011": {
        "content": "<|USER_2_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255012": {
        "content": "<|USER_3_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255013": {
        "content": "<|USER_4_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255014": {
        "content": "<|USER_5_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255015": {
        "content": "<|USER_6_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255016": {
        "content": "<|USER_7_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255017": {
        "content": "<|USER_8_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255018": {
        "content": "<|USER_9_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255019": {
        "content": "<|EXTRA_0_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255020": {
        "content": "<|EXTRA_1_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255021": {
        "content": "<|EXTRA_2_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255022": {
        "content": "<|EXTRA_3_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255023": {
        "content": "<|EXTRA_4_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255024": {
        "content": "<|EXTRA_5_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255025": {
        "content": "<|EXTRA_6_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255026": {
        "content": "<|EXTRA_7_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255027": {
        "content": "<|EXTRA_8_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      },
      "255028": {
        "content": "<|EXTRA_9_TOKEN|>",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": false
      }
    },
    "bos_token": "<s>",
    "clean_up_tokenization_spaces": false,
    "eos_token": "</s>",
    "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
    "legacy": true,
    "model_max_length": 1000000000000000019884624838656,
    "pad_token": "<PAD>",
    "sp_model_kwargs": {},
    "spaces_between_special_tokens": false,
    "tokenizer_class": "LlamaTokenizer",
    "unk_token": null,
    "use_default_system_prompt": false
  }