gec-spanish-BARTO-SYNTHETIC / tokenizer_config.json
SkitCon's picture
Upload model weights, config, and tokenizer files
1c77bed verified
raw
history blame
349 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 1024,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "BartTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}