-
In [this](https://www.tensorflow.org/tutorials/text/solve_glue_tasks_using_bert_on_tpu) tensorflow tutorial, there is a function - 'make_bert_preprocess_model' that returns a model mapping string feat…
Doyel updated
3 years ago
-
# 🐛 Bug
## Information
Albert tokenizers began crashing after I reorded my import statements with `isort`. Tracked down the bug to very strange behavior: importing `horovod.tensorflow` before `A…
-
**Describe the bug**
TypeError: build_callbacks() got multiple values for argument 'logger'
**Code to reproduce the issue**
```
import hanlp
from hanlp.datasets.classification.sentiment imp…
-
Hi,
I am getting an error if I set
```
os.environ['DISABLE_V2_BEHAVIOR'] = '1'
```
Below error doesn't come If I do not set it. I worked fine for `BERT` and `DistilBERT`.
```
ValueError …
-
안녕하세요, 며칠 전에 메일로 문의 드린 학생입니다. 먼저 답변 감사합니다.
문의 드리기 전에도 말씀하시대로 from_pt = True로 놓고 실행했었습니다. 코드는 README 4번 코드 그대로 사용했고
kb_albert_model_path = "model"만 추가했습니다. 실제로 pytorch 예제는 자 실행이 됩니다.
먼저 에러 내용은 다음과 …
-
Hi @saberkun, @zihangdai, @graykode, @bzantium
The original [zihangdai/XLNet](https://github.com/zihangdai/xlnet) repository doesn't get any update recently. Should we assume that the XLNet impleme…
-
**System information**
- Custom implementation of ALBERT for TF2.0
- Training on DataBricks
- TensorFlow installed from (source or binary): Binary pypi
- TensorFlow version (use command below): 2.…
-
Hello.
I have started the migration to tf2 for Kashgari V2.0. Here are the vision and roadmap.
## Same Principle
V2.0 will be based on the same vision for V1.0, which is to create a clean an…
-
# 🐛 Bug
## Information
The model conversion script `convert_pytorch_checkpoint_to_tf2.py` seems to be not working properly for ALBERT models.
It fails on the pre-trained models officially relea…
-
提问时请尽可能提供如下信息：
### 基本信息
- 你使用的**操作系统**: ubuntu 18.04
- 你使用的**Python**版本: Python 3.7
- 你使用的**Tensorflow**版本: TF 1.14.0
- 你使用的**Keras**版本: 2.4.3
- 你使用的**bert4keras**版本: 0.8.8
- 你使用纯**keras…