-
## 🐛 Bug
Model I am using (Bert, XLNet....): ALBERT
Language I am using the model on (English, Chinese....): English
The problem arise when using:
* [x] my own modified scripts: i'm fine…
-
# 🐛 Bug
Fresh Install errors out on import
## Information
Following from the README instructions, created a venv, installed torch and tensorflow. Installed transformers. Upon import
Model I a…
-
您好！首先感谢您的贡献。但是在实现的时候发现会有两个地方报错，一直不明白。
实现Albert时提示：KeyError: 'vocab_size'.
实现xlnet时提示：AttributeError: Layer Attention-Normal-24 has multiple inbound nodes, hence the notion of "layer output" is ill-d…
-
## Env：
python: 3.7.6
tensorflow: 2.1.0
bert4keras: 0.6.5
keras: 2.2.4-tf
## Replicate
```python
import os
os.environ["TF_KERAS"] = "1"
import tensorflow as tf
from tensorflow.keras.layers…
luoy2 updated
4 years ago
-
## ❓ Questions & Help
Hi~
```
bert_path = 'D:/pretrain/pytorch/albert_base/'
tokenizer = BertTokenizer.from_pretrained(bert_path)
BERT = BertModel.from_pretrained(bert_path)
...
with torch.no_g…
-
## 🐛 Bug
Model I am using (Bert, XLNet....): AlbertForQuestionAnswering
Language I am using the model on (English, Chinese....): English
The problem arise when using:
* [x] the official …
-
非常感谢您开源这个项目，在使用过程中遇到了一些问题想请教一下。
我在之前的项目都是通过 冻结BERT+lstm进行后续任务，所以huggingface/transformers中都是直接用
```
bert_path = 'D:/pretrain/pytorch/albert_base/'
tokenizer = BertTokenizer.from_pretrained(bert_pat…
-
I try to convert albert_zh(google version) to pytorch model, but it raise exception:
```shell
Loading TF weight cls/seq_relationship/output_weights/adam_v with shape [2, 312]
Loading TF weight gl…
-
## 🐛 Bug
Model I am using (Bert, XLNet....): ALBERT
Language I am using the model on (English, Chinese....): English
The problem arise when using:
* [ ] the official example scripts: (gi…
-
## 🐛 Bug
Model I am using: albert
Language I am using the model on (English, Chinese....): English
The problem arise when using:
* [X] the official example scripts: (give details)
examp…