poetry-bg / tokenizer_config.json
radi-cho's picture
add tokenizer
4d1e6de
raw
history blame contribute delete
614 Bytes
{
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"keep_accents": true,
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"name_or_path": "checkpoints/tokenizer8",
"pad_token": "<pad>",
"remove_space": true,
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"special_tokens_map_file": "/content/drive/MyDrive/ColabModels/GPT2_MEDIUM/pytorch_model/special_tokens_map.json",
"tokenizer_class": "AlbertTokenizer",
"unk_token": "<unk>"
}