tokenizer_config.json

{
  "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": "<bos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<eos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<user>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<assistant>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "<system>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<image>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "<graph>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "10": {
      "content": "<soft_token>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "11": {
      "content": "<vis_0>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "12": {
      "content": "<vis_1>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<pad>",
    "<unk>",
    "<bos>",
    "<eos>",
    "<mask>",
    "<user>",
    "<assistant>",
    "<system>",
    "<image>",
    "<graph>",
    "<soft_token>",
    "<vis_0>",
    "<vis_1>"
  ],
  "bos_token": "<bos>",
  "bos_token_id": 2,
  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<system>{{ message['content'] }}</system>\n{% elif message['role'] == 'user' %}<user>{{ message['content'] }}</user>\n{% elif message['role'] == 'assistant' %}<assistant>{{ message['content'] }}</assistant>\n{% endif %}{% endfor %}<assistant>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<eos>",
  "eos_token_id": 3,
  "extra_special_tokens": {},
  "mask_token": "<mask>",
  "mask_token_id": 4,
  "max_length": 512,
  "model_input_names": [
    "input_ids",
    "token_type_ids",
    "attention_mask"
  ],
  "model_max_length": 32000,
  "pad_to_multiple_of": null,
  "pad_token": "<pad>",
  "pad_token_id": 0,
  "pad_token_type_id": 0,
  "padding_side": "right",
  "special_tokens_map": {
    "additional_special_tokens": [
      "<pad>",
      "<unk>",
      "<bos>",
      "<eos>",
      "<mask>",
      "<user>",
      "<assistant>",
      "<system>",
      "<image>",
      "<graph>",
      "<soft_token>",
      "<vis_0>",
      "<vis_1>"
    ],
    "bos_token": "<bos>",
    "eos_token": "<eos>",
    "mask_token": "<mask>",
    "pad_token": "<pad>",
    "unk_token": "<unk>"
  },
  "stride": 0,
  "tokenizer_class": "PreTrainedTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>",
  "unk_token_id": 1
}