-
Could you please add some guide on how to reproduce the performance result?
For example, how to reproduce the result on the MSRA dataset?
Thanks.
-
这里的BERT预训练模型是怎样得到的？
或是
直接用BERT做分类任务，没有根据Masked LM和Next sentence 预训练？
-
运行时报错：
1
[F 8/21 15: 8:20.763 ...-Lite/lite/operators/fill_constant_op.cc:44 InferShapeImpl] no valid out_shape. Must set one of shape_tensor, or shape_tensor_list, or shape
代码：
from paddlelite…
-
-
使用`docker run -it -d --name trojan --net=host --restart=always --privileged jrohy/trojan init`指令创建容器，进入容器以后输入`trojan`开始初始化，但是安装过程中报错启动trojan失败！
-
我训练了两个epoch
输入：text = '中国保险资产管理业协会积极推进保险私[MASK]基金登记制改革落地实施'
输出：募
对于这个示例，我的预测结果是'事'
并且我尝试将text中的其他字MASK，预测出来也还是事
-
it seems pre-train corpus using whole word mask is not support in chinese yet.
even passing --do_whole_word_mask=True using create_pretraining_data.py, nothing happens.
is there someone know ho…
-
在运行api_v2.py时这个问题依然存在？请问怎么解决呀？
Traceback (most recent call last):
File "D:\ai\josencomfyui\GPT-SoVITS\api_v2.py", line 144, in
tts_pipeline = TTS(tts_config)
^^^^^^^^^^^^^^^
File "D:\ai\josenco…
-
As before discussion, i have try to replace the function in other language.
And i think about fine tuning the squad model you use to extract condition string
from question input (as the code says, y…
-
**Prerequisites**
* [x] Are you running the latest `bert-as-service`?
* [x] Did you check the [FAQ list in `README.md`](https://github.com/hanxiao/bert-as-service#speech_balloon-faq)?
* [x] Did…