-
大神，我想问下，electra-small, electra-large预训练的训练数据大概是多少？
-
您好，RoBERTa-wwm-ext, Chinese模型也是用BertModel.from_pretrained加载吗？是不是Huggingface-Transformers上用bert模型和RoBERTa模型的代码是一样的，我在BertModel.from_pretrained载入RoBERTa-wwm-ext, Chinese模型就相当于用的是RoBERTa模型了吗？很不理解，希望得到您的解…
-
Hello, thank you so much for your sharing. But When I test the converted ERNIE model using [pytorch-transformers](https://github.com/huggingface/pytorch-transformers), the performance on cloze task is…
-
大佬，怎么把别处下载的模型，载入到transformer代码里呢，我看到你的用的不是默认自带的模型。
-
# 🐛 Bug
## Information
Model I am using (Bert, XLNet ...): Bert
Language I am using the model on (English, Chinese ...): Chinese
The problem arises when using:
* [ ] the official example …
-
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [768] rhs shape= [1024]
[[Node: save/Assign_508 = Assign[T=DT_FLOAT, _class=["loc:@bert/e…
-
请问有没有在sentence-pair classification任务上进行过评测?我试了下效果相对于BERT官方(BERT-Base, Chinese)效果差很多
-
Hi,
Thanks for the nice work.
I downloaded a pre-trained Chinese RoBerta model. The model is pre-trained BERT like, containing 3 files, namely "config.json", "pytorch_model.bin" and "vocab.txt"
…
-
### 基本信息
**操作系统**: win10
**Python**版本: python3.6.5
**Tensorflow**版本: tensorflow-gpu 2.0.0
**Keras**版本: 2.3.1
**bert4keras**版本: 0.81.0
使用纯**keras**还是**tf.keras**: 什么导入库都没动,看样子是纯keras
加载的…
-
Why I couldn't use bert-serving-start load the model RoBERTa-wwm-ext-large? Sometimes Python stops running