-
## Environment info
- `transformers` version: 3.0.2
- Platform: macOS-10.15.6-x86_64-i386-64bit
- Python version: 3.8.3
- PyTorch version (GPU?): 1.5.1 (False)
- Tensorflow version (GPU?…
-
@patrickvonplaten, one of your recent PR (#6244) on Reformer introduces a dep on PyTorch 1.6.0 minimum by using `torch.cuda.default_generators`. We should see if we can find a way to work around this.
-
# 🐛 Bug
## Information
Model I am using (Bert, XLNet ...): reformer
Language I am using the model on (English, Chinese ...): english
The problem arises when using:
* [ ] the official exam…
-
### Description
According to the docs, the Reformer model expects two inputs: source and target. At HEAD it currently throws an error if it doesn't receive a third input. On a guess, I tried settin…
-
## Environment info
https://huggingface.co/transformers/main_classes/model.html
```resize_token_embeddings``` this documentation says it returns ```torch.nn.Embeddings``` The source code also us…
-
[Here](https://github.com/google/trax/blob/482c794a0e5a08960af82e74f8ca7f849583b58f/trax/models/reformer/reformer.py#L923) is your serial layer for the full reformer model:
```
return tl.Serial(
…
-
### Description
I trained the reformer model locally with version 1.3.1 and the config file: "reformer_wmt_ende".
When I'm trying to use it for inference in the colab:
https://colab.research.go…
-
This is not urgent. There is a ton of deprecation warnings across many modules with pytorch-1.7+ and a few with python-3.8:
(I hard-wrapped the lines to avoid the need to scroll, but it makes somewha…
-
## 어떤 내용의 논문인가요? 👋
본 논문에서는 locality-sensitive hashing, chunk-wise processing, reversible layers 등을 통해 efficient하게 Transformer을 훈련할 수 있게 만들었습니다.
## Abstract (요약) 🕵🏻♂️
Large Transformer models…
-
## Environment info
- `transformers` version: 3.1.0
- Platform: Linux 4.14
- Python version:3.7.9
- PyTorch version (GPU?):1.6.0 (True)
- Using GPU in script?: True
- Using distributed …