tokenizer_config.json

{
  "add_bos_token": false,
  "add_prefix_space": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<|startoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|endoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "errors": "replace",
  "lower": true,
  "name_or_path": "/data4/share_nlp/data/luannd/pretrained_model/gpt2-vietnamese",
  "pad_token": {
    "__type": "AddedToken",
    "content": "<|pad|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "special_tokens_map_file": null,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<|unk|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}