-
I used the parameters:
--data ETTh1
--method fsnet
--test_bsz 1
--seq_len 60
--pred_len 1
The training process works fine, but the testing error is as follows:
“RuntimeError: The size of tensor…
-
I am facing quite the same problem as in [https://github.com/pytorch/fairseq/issues/708](https://github.com/pytorch/fairseq/issues/708) at the moment when using multi-gpu training.
The training ha…
-
as the title
-
In OPUS 4 gibt es die Möglichkeit zwischen verschiedenen Layouts umzuschalten. Standardmäßig, wird das **opus4**-Layout verwendet. Die Layouts **default** und **plain** werden nicht verwendet und wurd…
-
The author didn't specify the requirements for environment. But most of the codes are borrowed from BertSum([https://github.com/nlpyang/BertSum](https://github.com/nlpyang/BertSum)) and Longformer([ht…
-
I have been experimenting with RWKV v4 and v4neo but somehow it is using much more memory (about 2x) than my LM that uses Flash Attention. Not sure what I am doing wrong. Is this expected?
-
Heya,
Thanks for your continued work in building better DEQs.
The main selling point of DEQs is that the solver can take as many steps as required to converge without increasing the memory. Thi…
polo5 updated
2 years ago
-
I have 6 titan GPUs machine with 12 GB memory, I changed the code to add my own dataset.
However, I always get cuda out of memory:
```
Run training...
Experiment dir : /home/agemagician/Downloads/…
-
@relhei
Wie besprochen: Wir sind nun in der Lage, erfolgreich URLs mit Weiterleitungen auf den KfL-Proxy zu generieren.
Folgende Punkte sollten wir noch klären:
1) Wie genau soll der Link im Fro…
-
0.5.0 0.27.1 2.0.0 1.23.5 3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:00:38) [MSC v.1934 64 bit (AMD64)] win32
```
Traceback (most recent call last):
File "F:\Users\miaoy\anaconda3…