Dr-Corgi

icon company South China University of Technology icon location Guangdong, China

Results 8 comments of Dr-Corgi

如何直接通过python调用你的rasa_nlu

官方文档里面有：https://nlu.rasa.com/python.html from rasa_nlu.model import Metadata, Interpreter from rasa_nlu.config import RasaNLUConfig interpreter = Interpreter.load(model_directory, RasaNLUConfig("sample_configs/config_spacy.json")) interpreter.parse(u"The text I want to understand")

如何直接通过python调用你的rasa_nlu

@xiaolong2009 需要自备梯子

entities must span whole tokens. Wrong entity end.

@crownpku 我这边用的应该是这个仓库最新的版本了，不过这两天在忙其他的事就没有仔细寻求解决方案。回头我也尝试一下楼上您提供的NER识别方法，看看能不能解决这个问题。谢谢！

what is pre-training dqn model and world model ? initialize Q(s; a; θQ) and M(s; a; θM) via pre-training on human conversational data？

I have the same question. lol

What's wrong with bernoulli?

I have found a solution in #285 It work for me.

[Bug] Training on 13B causes loss to be 0, while 7B works fine

hi, I faced the same problem and I fixed it by reinstalling the peft and transformers package.

ms-swift的维护

Good first issue √

Abnormal global_seqlen/max

same problem