-
Thanks for the work!
Is there any plan to focus on evaluations beyond traditional train/val/test splitting of data and running certain metrics? For example are there any plans to have model-based t…
-
Hi,
My intention is to develop a C++ project in Visual Studio (Windows) that runs the MarianMT model to translate from Spanish to English: https://huggingface.co/Helsinki-NLP/opus-mt-es-en.
For …
-
Hi,
My intention is to develop a C++ project that runs the MarianMT (onnx) model to translate from Spanish to English: https://huggingface.co/Helsinki-NLP/opus-mt-es-en. However, I'm stuck on how to …
-
I am trying to compile the MarianMT language translation model for `Inf1` instance.
```
kernel version = 5.4.228-131.415.amzn2.x86_64
Instance type on which the compilation was attempted = Inf1.2…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
### What happened?
将ControlNet升级到9月份的新版…
-
### System Info
Hi, I'm experiment some Transformer models for Translation task. These model are [vinai-translate-en2vi](https://huggingface.co/vinai/vinai-translate-en2vi), [wmt19-ru-en](https://h…
-
A common failure mode of the training is that the generation kwargs are not correctly set which leads to negative KL-divergence which is almost always a precursor for failed training. We should at lea…
-
## Roadmap:
1. Create IMAGE experiences in French (`IMAGE-server`)
- (1st sprint) Integrate a translation API to generate French output from English output
- (2nd sprint) Integrate the servic…
-
See MarianMT
[install PyTorch](https://pytorch.org/), then pip install sentencepiece and huggingface, the you can run:
```
from transformers import MarianMTModel, MarianTokenizer
from typing …
-
## Environment info
- `transformers` version: 4.12.2
- Platform: Linux-5.11.0-38-generic-x86_64-with-debian-bullseye-sid
- Python version: 3.7.2
- PyTorch version (GPU?): 1.10.0+cu102 (Fals…