-
《A Bottom-Up DAG Structure Extraction Model for Math Word Problems》AAAI 2021，framework and perspective are the same as you. They do not have Rationalizer and the other part of the model is the same as…
-
您好！请问现在models文件夹下的模型是基于math23k训练的么，方便把基于ape210k的预训练模型也公开下吗，谢谢~
wlkdb updated
3 years ago
-
跑math23k数据集的时候，用单机4卡跑，会在deepspeed init时hang住；关闭deepspeed也一样。
请问配置需要注意什么吗?
-
Thanks for the great work. Just wonder for the pre-trained Roberta-gen (Chinese version), which one do you use in the experiments for math23k.
-
Hi, I don’t know where to download the Math23K dataset. Can you can me? Thanks!
-
Hi,
May I ask how long did you train Math23K for an epoch? Your paper did not mention the concrete training time.
I tried to reimplement this paper. My dataset (4936 instances) needs around 10…
-
尚未进行任何修改，运行 run_seq2tree_APE.py 报错如下
start_from_epoch:101
last model acc:0.788
Traceback (most recent call last):
File "run_seq2tree_APE.py", line 171, in
encoder.load_state_dict(torch.loa…
-
Hi, It looks like you released codes to train and test the Math23K dataset only. How can I train and test on the AllArith dataset (and MAWPS)?