language:

• pt

该模型是从BERTimbau蒸馏得到的

使用方法

from transformers import AutoTokenizer  # 或 BertTokenizer
from transformers import AutoModelForPreTraining  # 或 BertForPreTraining 用于加载预训练头
from transformers import AutoModel  # 或 BertModel，用于不带预训练头的BERT
model = AutoModelForPreTraining.from_pretrained('adalbertojunior/distilbert-portuguese-cased')
tokenizer = AutoTokenizer.from_pretrained('adalbertojunior/distilbert-portuguese-cased', do_lower_case=False)

建议在您自己的数据上进行微调。

在某些任务中，其准确率可达原版BERTimbau的99%。

@misc {adalberto_ferreira_barbosa_junior_2024,
	author       = { {Adalberto Ferreira Barbosa Junior} },
	title        = { distilbert-portuguese-cased (版本 df1fa7a) },
	year         = 2024,
	url          = { https://huggingface.co/adalbertojunior/distilbert-portuguese-cased },
	doi          = { 10.57967/hf/3041 },
	publisher    = { Hugging Face }
}