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_middle|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163587": {
      "content": "<|im_user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163588": {
      "content": "<|im_assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "163594": {
      "content": "<|im_system|>",
      "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_user|>",
    "<|im_assistant|>",
    "<|im_system|>",
    "<|im_middle|>"
  ],
  "bos_token": "[BOS]",
  "clean_up_tokenization_spaces": false,
  "eos_token": "[EOS]",
  "extra_special_tokens": {},
  "model_max_length": 1048576,
  "pad_token": "[PAD]",
  "unk_token": "[UNK]",
  "tokenizer_class": "TikTokenTokenizer",
  "chat_template":"{%- for message in messages -%}{%- if loop.first and messages[0]['role'] != 'system' -%}<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>{%- endif -%}{%- if message['role'] == 'system' -%}<|im_system|>{%- endif -%}{%- if message['role'] == 'user' -%}<|im_user|>{%- endif -%}{%- if message['role'] == 'assistant' -%}<|im_assistant|>{%- endif -%}{{ message['role'] }}<|im_middle|>{{message['content']}}<|im_end|>{%- endfor -%}{%- if add_generation_prompt -%}<|im_assistant|>assistant<|im_middle|>{%- endif -%}",
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_moonshot.TikTokenTokenizer",
      null
    ]
  }
}