-
The first round of research was not too positive, but more is needed to fully test this path out. It appears that SILNLP may also be broken for fine tuning on multiple language pairs.
-
Ideas to enable this could be:
* Train a model with the mid-verse USFM tokens (or replacement tokens) that it learns to place properly.
* Reinsert the USFM after generation of the draft by using the…
-
Facebook just released a new multimodal model for multiple languages. I would assume it's the successor to NLLB. _One model to rule them all_. It would be amazing to have CT2 support for this to furth…
-
I run the program in pycharm, one error listed below occurs, how to solve it?
ValueError: Unrecognized model in weights/icon_caption_florence. Should have a `model_type` key in its config.json, or co…
-
## ❓ Questions and Help
I found training or finetuning NLLB requires Slurm cluster environment, what should I do if I just want to train/finetune a small NLLB model?
### Before asking:
1. searc…
-
- Advanced type of Language Model using Deep learning techniques using heavy text data.
- Capable of generating human like text. QnA, Text2Text
- Concepts like n-gram to Neural Networks are used. …
-
1. Install plugin in OBS
2. Setup models:
- model: nllb-200-distilled-600M-int8
- SPM: flores200_sacrebleu_tokenizer_spm.model
3. Start service "Start / Stop HTTP Server"
4. Make some re…
-
.unsupportedTokenizer("NllbTokenizer")
-
Hi,
NLLB is good start, however, there are many other opensource models that were released in last few years. Wikimedia Foundation has been providing a machine translation service based on a collecti…
-
There is [great research](https://drive.google.com/file/d/1cS9OYLgqTALDVvN9pMk6t-KD3UiQ-e42/view) from Taeho Jang that we could get a 10pnt Bleu score bump from using a common script instead of an unc…