-
When attempting to import the Multilabel Classification Model I receive an error that the MT5 tokenizer is not defined. Similarly to another issue the following code also produces errors:
from sim…
-
Hello,
when I run the fine-tuned mt5 model under onnx, I get the following error:
`TypeError Traceback (most recent call last)
in
----> 1 model.onnx_predict(te…
-
Hi,
Thanks for the amazing simpleT5 package. I use the following script to train a mt5 model for summarization task.
`from simplet5 import SimpleT5`
`model = SimpleT5()`
`model.from_pretr…
-
I want to use a multilingual model (in my case MT5) to train it for two languages (English and German).
These models have a very high vocab size because they are multilingual.
This large embedding n…
-
MT5-large model [config](https://huggingface.co/google/mt5-large/blob/main/config.json) has wrong parameters `"architectures"` and `"tokenizer_class"` as
```json
{
"architectures": [
"T5Fo…
-
hi there,
it seems that the newest version of simpleT5 does no longer work with byT5. The line `elif model_type == "byt5":` is commented out. The newest version of transformers seems to use a new typ…
-
**Describe the bug**
When running inference on two models in one script, the second model will generate gibberish instead of what it would normally generate.
**To Reproduce**
Steps to reproduce t…
-
T5 encoder中的self attention是不是没有添加MASK？
-
Why there is no training example for T5 or MT5???
Could you please give me a link to an example? I had a hard time to write a code with various errors:
This is my code:
```
import torch
from dat…
-
### 1. System information
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 18
- TensorFlow installation (pip package or built from source): pip
- TensorFlow library : 2.3.1…