-
-
I did pip install --no-cache-dir sentencepiece
but when I try to import it in Python 3.9, it crashes with :
ImportError: dlopen(/Users/olivier/miniforge3/lib/python3.9/site-packages/sentencepiece/_s…
-
@jmhessel @dirkgr @schmmd @iellenberger
Ran python scripts/training/train_text_generation.py --config_path scripts/training/task_configs/iwslt2017/t5_ppo.yml
with the following config:
`…
-
Hey @versae in the new paper scale efficiently https://arxiv.org/abs/2109.10686
There are better, efficient variants of T5 and mT5 but i couldn't find these efficient models in the T5x repo.
If i h…
-
- [x] Прогнать выбранные ранее семплы новостей (30 шт. и 10 шт.), через наиболее подходящие модели суммаризации, итоговые результаты свести в единую таблицу;
- [x] Провести анализ результатов, на пре…
-
### Description
```shell
After using triton fastertransformer backend, the same model and the same data are much slower than torch code.
model: mt5
```
### Reproduced Steps
```shell
result:
…
-
### Checklist before your report.
- [X] I have verified that the issue exists against the `master` branch of AdaSeq.
- [X] I have read the relevant section in the [contribution guide](https://github.…
-
Can I training a bart model from scratch by transformers?
-
I am trying to finetune the mt5-small with Telugu corpus, all the generated summaries includes tokens, please suggest how to fixt it.
Example generated output:
హోమియోపతి కళాశాలను న్యూఢిల్లీ సె…
-
## Memtest86+
* Fails immediately with `Unexpected interrupt on CPU 0`
* Running v6.01 from public 64-bit iso (32-bit also produces the error)
* Booting as legacy BIOS boot over virtual USB CDROM (…