ymcui/Chinese-BERT-wwm Issues
有点晕：『开源版本不包含MLM任务的权重』,这句话是什么意思？
Closed 3RoBERTa-wwm-ext-large应用到全新领域不收敛
Closed 4从BERT换成此模型后跑不通，应该怎么解决，显示缺少参数
Updated 1请问每个模型推理时需要多大的显存去加载？
Closed 1Is onnx model available
Closed 2NER问题
Closed 2请问可否使用wwm系列的模型做词级别的fill-mask预测？
Closed 2预训练数据
Closed 2如何抽取特定layer的词向量？
Closed 2继续预训练
Closed 2关于不能用RobertaModel引用
Closed 8How WWM stratege works in code
Closed 2链接失效求助
Closed 2CJRC有预训练的模型么？
Closed 1请问一下训练用了几块tpu呀
Closed 2预训练阶段的loss问题
Closed 2wwm mask 细节
Closed 2关于词表没有中文双引号的问题
Closed 3EXT数据集的量有多少
Closed 1词汇级词向量
Closed 1pad_token_id错误
Closed 5请问BERT-wwm-ext有使用nsp任务吗？
Closed 2计算两句子的相似度
Closed 2讯飞的下载链接提示外链已经过期了
Closed 4有没有Bert-wwm-ext-large模型?
Closed 2rbt3将tf模型转torch报错
Closed 2求问不同模型的schedule细节
Closed 2roberta中cls token的计算方法
Closed 3求教：为什么词语要对应多个mask？
Closed 3> @beamind 请问复现结果了吗
Closed 2序列标注任务警告信息
Closed 2这个模型可以不做fine-tuning直接用吗？
Closed 2如何获得词向量？
Closed 2实验结果复现问题
Closed 2tokenizer
Closed