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": "<|end_of_msg|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163587": {
      "content": "<|open|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "163588": {
      "content": "<|close|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "163589": {
      "content": "<|sep|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "163590": {
      "content": "[start_header_id]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163591": {
      "content": "[end_header_id]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163593": {
      "content": "[EOT]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163602": {
      "content": "<|media_begin|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163603": {
      "content": "<|media_content|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163604": {
      "content": "<|media_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163605": {
      "content": "<|media_pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163649": {
      "content": "<osagent_mode>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163838": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163839": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|end_of_msg|>",
    "[start_header_id]",
    "[end_header_id]",
    "[EOT]",
    "<|media_begin|>",
    "<|media_content|>",
    "<|media_end|>",
    "<|media_pad|>",
    "<osagent_mode>"
  ],
  "bos_token": "[BOS]",
  "clean_up_tokenization_spaces": false,
  "eos_token": "[EOS]",
  "extra_special_tokens": {},
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "tokenizer_class": "TikTokenTokenizer",
  "unk_token": "[UNK]",
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_kimi.TikTokenTokenizer",
      null
    ]
  }
}