tokenizer/tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "49406": {
      "content": "<|startoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49407": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "49408": {
      "content": "<tangyuan>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49409": {
      "content": "<tangyuan>_1",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49410": {
      "content": "<tangyuan>_2",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49411": {
      "content": "<tangyuan>_3",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49412": {
      "content": "<tangyuan>_4",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49413": {
      "content": "<tangyuan>_5",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49414": {
      "content": "<tangyuan>_6",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49415": {
      "content": "<tangyuan>_7",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49416": {
      "content": "<tangyuan>_8",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "49417": {
      "content": "<tangyuan>_9",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<|startoftext|>",
  "clean_up_tokenization_spaces": true,
  "do_lower_case": true,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "model_max_length": 77,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "CLIPTokenizer",
  "unk_token": "<|endoftext|>"
}