-
# 🌟New model addition
## Model description
Yesterday, Facebook has released _open source_ its new NLG model called **XLM-R** (XLM-RoBERTa) on [arXiv](https://arxiv.org/abs/1911.02116). This mode…
-
## 🐛 Bug
I use torch.hub.set_dir(localdir) in order to avoid having the model files hidden in `.cache/torch/pytorch_fairseq/3f864e15bb396f062dd37494309dbc4238416edd1f8e...`, but only `pytorch_fairs…
-
## 🐛 Bug
When using XLM-R the representations change depending on the batch size.
#### Code sample
```
from fairseq.models.roberta import XLMRModel
from torchnlp.encoders.text import stack_and_…
-
## 🐛 Bug
when running
```python
from fairseq.models.roberta import XLMRModel
xlmr = XLMRModel.from_pretrained('/path/to/xlmr.large', checkpoint_file='model.pt')
ids = xlmr.encode('Hello worl…
-
## ❓ Questions and Help
I want to finetune XLM-R language model on my additional **monolingual** dataset. After some research, I think my steps are:
- Preprocessing:
+ Follow `prepare-iwslt17-mul…
-
Hi,
It seems that there is a problem with the new XLM-R large archive available from: https://dl.fbaipublicfiles.com/fairseq/models/xlmr.large.tar.gz
It returns a file of size 1.1GB and there is a…
-
## 🐛 Bug
Long story short, I've trained roberta using a custom dictionary and now I am trying to extract features (code snippet below for reference).
```python
roberta = RobertaModel.from…
-
I will study squad of multilingual.
I found that question answer package did include in run_squad.py.
I wanna release that package
Are you plan to release XLMRobertaForQuestionAnwering?
pl…
-
Hi,
thanks for releasing the final base and large models for XLM-RoBERTa.
Unfortunately, the models can't be loaded from `torch.hub`:
```python
import torch
xlmr = torch.hub.load('pytorch/…
-
Hi,
How can I find similarity score between two different languages?
### Example,
> Sentence 1 (English)
> Sentence 2 (Hindi )
> Similarity score between 0 and 1.
Using `xlmr.large`
Best…