Nlp 无法导入';AutoModelForSequenceClassification';从';变压器';
无法从“transformers”导入“AutoModelForSequenceClassification” 代码是Nlp 无法导入';AutoModelForSequenceClassification';从';变压器';,nlp,huggingface-transformers,transformer,Nlp,Huggingface Transformers,Transformer,无法从“transformers”导入“AutoModelForSequenceClassification” 代码是 from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline t = AutoTokenizer.from_pretrained('/some/directory') m = AutoModelForSequenceClassification.from_pretrai
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
t = AutoTokenizer.from_pretrained('/some/directory')
m = AutoModelForSequenceClassification.from_pretrained('/some/directory')
c2 = pipeline(task = 'sentiment-analysis', model=m, tokenizer=t)
错误是
cannot import 'AutoModelForSequenceClassification' from 'transformers'
从transformers导入AutoModelForSequenceClassification,BertForSequenceClassification
从transformers导入(XLMRobertaConfig、XLMRobertaTokenizer、TFXLMRobertaModel)
从变压器进口自动煮锅、自动配置、TFAutoModel
预训练的\u模型\u类型={
'xlmroberta':(自动配置、序列分类自动建模、自动烹饪器,'akhooli/xlm-r-large-arabic-toxic')
}
#model_class,model=AutoModelForSequenceClassification.来自预先训练的(“akhooli/xlm-r-large-arabic-toxic”)
配置类、模型类、标记器类、模型名称=预先训练的模型类型['xlmroberta']
#从huggingface.co和cache下载词汇表。
代币器=自动代币器。来自预训练(型号名称,使用快速代币器=假)#快速代币器
tokenizer
什么是transformers版本?它现在正在工作。我已经安装了4.3.3