pruebaModeloTFM_Roberta_in / tokenizer_config.json
pamelapaolacb's picture
Training in progress, epoch 0
cb11866
raw
history blame contribute delete
542 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"max_length": 384,
"model_max_length": 512,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "</s>",
"stride": 128,
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"truncation_side": "right",
"truncation_strategy": "only_second",
"unk_token": "<unk>"
}