tokenizer_config.json

{
  "added_tokens_decoder": {
    "163584": {
      "content": "[BOS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163585": {
      "content": "[EOS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163586": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163601": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163587": {
      "content": "[SPECIAL_000]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163588": {
      "content": "[SPECIAL_001]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163594": {
      "content": "[SPECIAL_002]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163838": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163839": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_end|>",
    "<|im_start|>",
    "[SPECIAL_000]",
    "[SPECIAL_001]",
    "[SPECIAL_002]"
  ],
  "bos_token": "[BOS]",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "extra_special_tokens": {},
  "model_max_length": 1048576,
  "pad_token": "[PAD]",
  "unk_token": "[UNK]",
  "tokenizer_class": "TikTokenTokenizer",
  "chat_template":"{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_moonshot.TikTokenTokenizer",
      null
    ]
  }
}