-
Hi,
When I am trying validation for small questions in the GECOR model and I am getting repeated words in the final output. I will provide couple of examples:
1:
user : What is the price of pi…
-
# 🚀 Feature request
As we're called `transformers`, it would be nice if there's a `Transformer` class that is not associated with any pretrained model and that we can directly instantiate, like
`…
-
# 在ai studio中运行如下代码:
```
!python ERNIE/demo/seq2seq/finetune_seq2seq_dygraph.py \
--from_pretrained ernie-1.0 \
--data_dir work/datasets/medical \
--max_steps 128 \
--save_dir work/save
```
…
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Google Colaboratory
- TensorFlow version and how it was installed (source or binary): 2.4.1
- TensorFlow-Addons ver…
-
# ❓ Questions & Help
## Details
-
Trying master on another machine I get:
```
Traceback (most recent call last):
File "examples/seq2seq/run_seq2seq.py", line 650, in
main()
File "examples/seq2seq/run_seq2seq.py", line 590,…
-
Hi, I'm trying to fine-tune T5 model with the scripts in [transformers/examples](https://github.com/huggingface/transformers/tree/master/examples) folder.
```sh
git clone https://github.com/huggin…
-
tensorflow 1.15 has a function "tf.contrib.seq2seq.AttentionWrapper", but as we know tf.contrib module is no longer available in TensorFlow 2.0. I find "tfa.seq2seq.AttentionWrapper" may replace "tf.c…
-
**Describe the bug**
I tried to train Stanza for Tamil, and mwt training always (tried with different data set) breaks at 33rd epoch.
Log:
2020-08-20 09:24:11: step 360/1100 (epoch 33/100), loss = …
-
## Environment info
- `transformers` version: 4.1.1
- Platform: Linux-4.15.0-99-generic-x86_64-with-glibc2.27
- Python version: 3.8.0
- PyTorch version (GPU?): 1.7.1 (True)
- Tensorflow …