leilai li

some question about DKRL

10

hello , bxshi: could you share the running time about the model of dkrl in your code, and i notice that in your paper, the statistic of dkrl is different...

Question about the experiments result

5

hi~ i have re-implement your code on vrd with the default parameters , and getting a result。The result does not accord with the paper, and the result as follows: Epoch...

Does any plans to support the Pegasus for summary

1

does any plans to support the Pegasus for summary, thanks

编译过程碰到的问题

14

按照编译的文档：https://github.com/bytedance/lightseq/blob/master/docs/inference/build.md 碰到了下面的问题，请问可以怎么解决？ 

hi~ the url of downloading us8k datset can not connected. So,could you provide another way to get this ds. Looking forward you reply thank you

关于数据集和代码的一些问题

6

你好～ 在恢复实验的过程中，碰到了问题，期望你能解答一些。 根据您给定的代码和预训练的模型，在数据集PIPA上进行测试，出现如下的错误: self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for GRM: Missing key(s) in state_dict: "ggnn.reason_fc_x.bias", "ggnn.reason_fc_x.weight", "ggnn.reason_fc_y.bias", "ggnn.reason_fc_y.weight", "ggnn.reason_fc2.bias", "ggnn.reason_fc2.weight". size mismatch for classifier.1.weight: copying a param of...

loading data error

4

Hi~ i try to reimplement your released code, but i meets this error as follows. looking forward your reply *************************************************** Load ESC_50 from ../data/ESC_sep.npy Bus error (core dumped) ***************************************************

关于代码的问题

2

你好～ 在恢复实验的过程中，碰到了问题，期望你能解答一些。 根据您给定的代码和预训练的模型，在数据集PIPA上进行测试，出现如下的错误: self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for GRM: Missing key(s) in state_dict: "ggnn.reason_fc_x.bias", "ggnn.reason_fc_x.weight", "ggnn.reason_fc_y.bias", "ggnn.reason_fc_y.weight", "ggnn.reason_fc2.bias", "ggnn.reason_fc2.weight". size mismatch for classifier.1.weight: copying a param of...

I make an attempts to run this method on A100， and i have meet error as follow pic. And, i test torch-1.3.1 and torch-2.0.0 that both of them could produce...

How to implement this method combinded with decoder

2

Details: 1、the open souce code only support first round text input, if we set the past_key_values=True, and we can not got the error because the dims of attention mask not...