weizhen.zhao

run demo.py wrong

5

Hi Dear when I run python demo.py it shows the following error: [root@localhost sceneReco]# python demo.py Traceback (most recent call last): File "demo.py", line 2, in from ctpnport import *...

Hi dear I ran your reposity , but it shown some error . I find there is no data under data/train/feat/ directory can you help with me? Thanks weizhe

rasa_nlu.train needs an url?

1

root@weizhen-Lenovo-IdeaPad-Y470:/home/weizhen/Rasa_NLU_Chi# python -m rasa_nlu.train -c sample_configs/config_jieba_mitie_sklearn.json usage: train.py [-h] [-o PATH] (-d DATA | -u URL) -c CONFIG [-t NUM_THREADS] [--project PROJECT] [--fixed_model_name FIXED_MODEL_NAME] [--storage STORAGE] [--debug] [-v] train.py: error:...

你好我遇到一个拒绝访问的问题，当执行python setup.py 的时候 具体的log 如下所示，万望楼主哥哥帮忙看一看，小弟不胜感激。 另外楼主哥哥真的超级厉害呀 `creating build\bdist.win-amd64\egg\EGG-INFO copying rasa_nlu.egg-info\PKG-INFO -> build\bdist.win-amd64\egg\EGG-INFO copying rasa_nlu.egg-info\SOURCES.txt -> build\bdist.win-amd64\egg\EGG-INFO copying rasa_nlu.egg-info\dependency_links.txt -> build\bdist.win-amd64\egg\EGG-INFO copying rasa_nlu.egg-info\requires.txt -> build\bdist.win-amd64\egg\EGG-INFO copying rasa_nlu.egg-info\top_level.txt -> build\bdist.win-amd64\egg\EGG-INFO zip_safe flag...

hi 您好 如何把豆瓣开源的对话数据应用到这个multiTurnResponseSelection上面呢？ 十分感谢 Thanks weizhen

GPT3 跑官方给的代码 一直卡在> compiling and loading fused kernels ...

2

GPT3 跑官方给的代码 一直卡在> compiling and loading fused kernels ... 没有反应 看阿里云上面说是因为 编译的时候有锁冲突了？ 能不能告诉应该删除哪个临时文件夹？ 具体应该怎么解决呀？ 一直加载不了 感激不尽。

你好，我在gpu上面使用paddlepaddle的dureader mrc版本，去训练的模型， 然后在gpu上面去加载模型预测的时候，没有问题， 但是在cpu上面加载模型的时候就报下面这个错误， paddle的版本是1.2.0 这个paddlepaddle版本中的predict方法，在cpu上面你们测试过好用吗？ 能否帮忙看看呀？感激不尽 paddle.fluid.core.EnforceNotMet: Cannot open file models/4/4\pn_decoder:fw:static_rnn:_lstm_f_b for load op at [E:\dist\Paddle\paddle\fluid\operators\load_op.cc:39]

添加滑动窗口

1

https://github.com/ssbuild/deep_training/blob/cb95857b366cbd3a03c1e8c9fd468ffd8b3f0bda/nlp/models/chatglm/__init__.py#L1167 大佬 冒昧问下，这里可不可以添加一个滑动窗口呀？ 滑动最近3轮对话，这样会保证对话长度在一定的范围以内。 Thanks weizhen

Hi dear After I download the comma-dataset , I can not find keys start with 'app_' in the log directory file which you wrote in your log.md. is there something...

https://github.com/CarperAI/trlx/blob/9fdd0d757e8f7a3d48e7edb060ddb7517da13d2d/trlx/trainer/accelerate_ppo_trainer.py#L399 I met that error when precompute logprobs, values due to the concatenation of prompt_tensor and output . my question is why we concat the prompt_tensor and output in the...