Catalan_language-clustered / tokenizer_config.json
nandysoham16's picture
Training in progress epoch 0
986f9b8
raw
history blame contribute delete
366 Bytes
{
"cls_token": "[CLS]",
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "nandysoham16/13-clustered_aug",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "DistilBertTokenizer",
"unk_token": "[UNK]"
}