-
Updated (October 23)
- 14K github models (72%) (https://github.com/jansel/pytorch-jit-paritybench)
- [x] #111691
- [ ] #111693
- [ ] 153 errors like: AssertionError: Failed to produce a gr…
-
您好,感谢您的开源贡献,我有下面几个问题还请您能够解答一下:
1.您的.sh默认是将标准、低资源两种模式都执行吗?假如要进行特定实验(比如16-shot下的semeval.sh),参数该如何修改?
2.目前我看semeval数据集中有19种关系类型,但是train.txt文件双向关系数据中,没有“Entity-Destination(e2,e1)”关系类型的数据,而仅有“Entity-Dest…
-
您好!请教您几个问题:
1、我看到了除了bert基础模型,还有基于bert模型训练出来的cnSchema模型外,还有[LightNER(COLING'22)]、 [W2NER(AAAI'22)] 、[KnowPrompt(WWW'22)], [PRGC(ACL'21)], [PURE(NAACL'21)]等模型,作为中文提取,哪个模型最优?或者能否基于cnSchema模型继续训练和微调。从目前看…
-
大佬好!首先对你们的卓越工作以及开源精神表示敬意!
起因:我在尝试重新运行项目中的代码的时候,对 KE loss 的有效性有一些疑问,虽然论文中你们提到“In addition, there exists rich semantic knowledge among relation labels and **structural knowledge** implications among …
-
-
It seems that the virtual type words and soft prompt are the same thing, except that virtual type words are initialized according to the prior probability distribution.
May I know whether my underst…
-
而且已经把reberta-large模型下载到本地,也更改了main.py中的from_pretrain()的地址,还是报错
-
**Describe the question**
想请问一下RE few-shot中,按照所给步骤操作(即下载数据集SEMEVAL,运行run.py训练模型),运行predict.py后,得到的f1分数对应的是KnowPrompt论文哪个部分的结果,不知道复现的有没有问题。
**Environment (please complete the following inform…
-
Hello, thank you very much for being able to open source code!!! But it seems that there is no SLM related code provided here, I wonder if it can be provided?
-
尝试了几个数据集,都是在最后两个epoch时报错:FileNotFoundError: [Errno 2] No such file or directory: '/home/code/KnowPrompt/output/epoch=2-Eval/f1=0.906.ckpt',求指点