-
#### What is your question?
How to extract_feature with XLMR using multiple GPU? If I use the following code with DataParallel() I can only utilize a single GPU..
#### Code
xlmr = torch.hub.loa…
-
There seems to be an inconsistency in encoding returned by hub_interface and bpe model. The sentencepiece encodings seem to be off by one. Here are the code snippets:
import torch
xlmr…
-
Hi, thanks for the benchmark and the accompanied code!
I am trying to replicate XQUAD scores from the (XTREME) paper using this repo's code.
I run ```mBert cased``` model with default parameters …
-
Are the pre-trained models on this repository "Multilingual" versions of SpanBERT or only English? if not, is there any multilingual version available?
-
## 🐛 Bug
I am witnessing `ImportError: cannot import name 'libbleu'`, when running this [torch hub translation example on Google Colab](https://colab.research.google.com/github/pytorch/pytorch.gith…
-
For example:
### setup
```python
import torch
xlmr = torch.hub.load('pytorch/fairseq', 'xlmr.large')
xlmr.eval()
```
## Test
```python
sent1 = "this is a good sentence"
sent2 = "*%&^( so…
-
I have tried exporting the xlmr.base model from torch.hub to onnx, but I receive an exception regarding ATen.
```
%output : Float(1, 5, 768) = onnx::Transpose[perm=[1, 0, 2]](%1188), scope: Expo…
-
I am trying to train an XLM-R model in Kaggle Kernels with TPU enabled. There was a TF kernel that was able to do this successfully:
https://www.kaggle.com/xhlulu/jigsaw-tpu-xlm-roberta
However, a…
-
Hi,
Let's start a discussion here about the roadmap towards 0.10 and 1.0. We are looking for:
- New features that are useful to your research
- Improvements and patches to existing features
If…
-
I used datasets and dataloaders a lot before with text (fastaiv2 0.0.8), be it for custom datasets with standard ULMFIT use, be it for using transformers adapted to fastaiv2 pipeline.
I recently up…