-
I am very interested in multilingual embedding models. But there is no converted multilingual model. According to comments of the example sentence_embeddings_local, I converted many models successfull…
-
Thanks for the great Repo.
In the mentioned repo https://github.com/hyunwoongko/asian-bart
He is doing Mbart embedding layer pruning. I want to do the same for a particular language.
Any suggesti…
-
### Problem description
The chinese language has some special characters for parentheses: "（", "）" (= parentheses with an integrated whitespace). Both characters aren't part of the XLMRoBERTa Toke…
-
I'm not sure if this is where this is supposed to go but, at the highest level,
I'm using `rust-bert` and trying to instantiate an `NERModel` with seemingly
default `XLMRoberta` configurations like:…
-
## ❓ Questions and Help
### Before asking:
1. search the issues.
2. search the docs.
#### What is your question?
I am a beginner in python and just learning about fairseq. I wan…
-
Hello,
I need your advice on usability of bicleaner ai in my situation.
I have around 100k Abkhazian-Russian parallel corpus with 85% accuracy rate 85% (15% is wrong translation).
I have 1.2 mi…
-
**Describe the bug**
Thanks for maintaining the library.
I cannot download tokenizer files for [TransQuest/monotransquest-hter-en_any](https://huggingface.co/TransQuest/monotransquest-hter-en_an…
-
**Describe the bug**
`from simpletransformers.ner import NERModel, NERArgs`
When I provide `model_args.num_train_epochs = 5` the model `metadata` shows only 5 epochs and also the live progress shows…
-
when i run `kiwi train config/xlmroberta.yaml`
I have encountered the following problems
> /pytorch/aten/src/THC/THCTensorIndex.cu:272: indexSelectLargeIndex: block: [43,0,0], thread: [32,0,0] Ass…
-
### System Info
```shell
- `transformers` version: 4.19.1
- Platform: Linux-5.13.0-39-generic-x86_64-with-glibc2.31
- Python version: 3.10.0
- Huggingface_hub version: 0.6.0
- PyTorch version …