-
## Environment info
- `transformers` version: 3.3.1
- Platform: Linux-4.19.112+-x86_64-with-Ubuntu-18.04-bionic
- Python version: 3.6.9
- PyTorch version (GPU?): 1.6.0+cu101 (False)
- Te…
-
The examples of how to use seq2seq decoders decoders, in particular the beam search one available in the readme https://github.com/tensorflow/addons/tree/master/tensorflow_addons/seq2seq are not suffi…
-
Greetings!
I have used custom_transformer_training and created a Transformer Model for translation .
The code is mentioned below:
```
import logging
import tensorflow as tf
import tensorflo…
-
Hi
I am getting this error when evaluating on wmt16-ro-en using finetune_trainer.py of huggingface repo. thank for your help
{'epoch': 20.0} …
-
**Issue by [yukatherin](https://github.com/yukatherin)**
_Tuesday Jul 17, 2018 at 23:40 GMT_
_Originally opened as https://github.com/nyu-mll/jiant/pull/184_
----
I believe all comments on https://…
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows 10 (64-bit)
- Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device…
-
## Environment info
- `transformers` version: 3.3.1
- Platform: Linux-4.4.0-1113-aws-x86_64-with-debian-stretch-sid
- Python version: 3.7.9
- PyTorch version (GPU?): 1.3.1 (True)
- Tenso…
-
Hi and thanks for making a great project!👍
When I tried seq2seq decoder with LocationAwareAttention, I found possibly unexpected broacasting caused by AddNorm.
https://github.com/sooftware/KoSpeec…
-
After repeated your example,
```
sh scripts/exe_post.sh out
```
the system has thrown errors as following.
```
Traceback (most recent call last):
File "src/main.py", line 161, in
…
-
## Description
We are using Node.js to coordinate processes, including a Python web server that loads a pretrained model in CPU mode.
The model files are downloaded and cached prior to execution…