tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "128244": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151643": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151644": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151645": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151646": {
      "content": "<image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151647": {
      "content": "</image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151648": {
      "content": "<ref>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151649": {
      "content": "</ref>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151650": {
      "content": "<box>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151651": {
      "content": "</box>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151652": {
      "content": "<quad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151653": {
      "content": "</quad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151654": {
      "content": "<point>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151655": {
      "content": "</point>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151656": {
      "content": "<slice>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151657": {
      "content": "</slice>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151658": {
      "content": "<image_id>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151659": {
      "content": "</image_id>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151660": {
      "content": "<NUM>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151661": {
      "content": "<|reserved_special_token_1|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151662": {
      "content": "<|reserved_special_token_2|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151663": {
      "content": "<|reserved_special_token_3|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151664": {
      "content": "<|reserved_special_token_4|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151665": {
      "content": "<|reserved_special_token_5|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151666": {
      "content": "<|reserved_special_token_0|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<image>",
    "</image>",
    "<ref>",
    "</ref>",
    "<box>",
    "</box>",
    "<quad>",
    "</quad>",
    "<point>",
    "</point>",
    "<slice>",
    "</slice>",
    "<image_id>",
    "</image_id>",
    "<|reserved_special_token_0|>",
    "<|reserved_special_token_1|>",
    "<|reserved_special_token_2|>",
    "<|reserved_special_token_3|>",
    "<|reserved_special_token_4|>",
    "<|reserved_special_token_5|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_minicpmv_fast.MiniCPMVTokenizerFast",
      null
    ]
  },
  "bos_token": "<|im_start|>",
  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|endoftext|>",
  "split_special_tokens": false,
  "tokenizer_class": "MiniCPMVTokenizer",
  "unk_token": "<unk>"
}