-
train on 30000000 parallel english and chinese sentences, after trained 100000 steps, the predit result:
![image](https://user-images.githubusercontent.com/37894838/148315788-ed26c456-d86f-4b21-b2d3-…
-
**Describe the question**
> A clear and concise description of what the question is.
File "C:\Users\DuYH\AppData\Local\Programs\Python\Python38\lib\site-packages\transformers\tokenization_utils_…
-
(cuda1100) [qyh@localhost tts3]$ CUDA_VISIBLE_DEVICES='4' ./local/inference.sh ./train
[nltk_data] Error loading averaged_perceptron_tagger:
[nltk_data] Error loading cmudict:
/home/qyh/anaconda3…
-
# 🐛 Bug
## Information
Model I am using (Bert, XLNet ...): Bart (bart-large-cnn)
Language I am using the model on (English, Chinese ...): English
The problem arises when using:
* [ ] the …
-
### 请提出你的问题
在paddle里运行2021 CCF BDCI 千言-问题匹配鲁棒性评测Baseline时, 运行至
import paddlenlp as ppnlp报错: TypeError: can't apply this __setattr__ to type object
-
### What problem are you trying to solve?
We download the required files for unit tests in the `make prepare-transformers` target. See [here](https://github.com/RasaHQ/rasa/pull/7768). However, there…
-
Token to id conversion works fine, but text to ids conversion fails.
```python
print(sp.id_to_piece(2))
print(sp.piece_to_id(""))
print(sp[""])
print(sp.encode(""))
print(sp.decode(sp.encode("…
-
### System Info
Linux Debian,
bert-base-multilingual-cased,
bert-base-chinese
### Who can help?
@SaulLu
@LysandreJik
@ArthurZucker
### Information
- [X] The official example scripts…
-
I want to train a joint Chinese and English model. And predefine common use Chinese chars like this (totally 7000 chars).
```
一
丁
七
万
丈
三
上
下
不
与
丐
丑
```
I train the model by this comma…
-
## Environment info
- `transformers` version: 4.1.1
- Platform: Linux-4.14.105-1-tlinux3-0013-x86_64-with-centos-7.2-Final
- Python version: 3.7.7
- PyTorch version (GPU?): 1.5.1 (True)
- Ten…