Shivanand Roy comments

Results 14 comments of


                                            Shivanand Roy

ValueError: text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples).

Would you mind sharing a colab notebook. i will take a look.

ValueError: text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples).

T5 models are text to text models & they expect `source_text` and `target_text` to be a string. I would suggest to make sure your dataframe has values in string format....

Unicode Charecter training issue

@rahat10120141 : How does your `train_df` looks like before feeding to model?

ValueError: transformers.spec is None

fixed in #13 ```python # pip install simplet5 from simplet5 import SimpleT5 model = SimpleT5() ``` Thanks for pointing out

Metrics and logging.

I will include wandb integration in the next release !!

@Sripaad Sorry for late reply. Now, SimpleT5 (latest pre-release) supports all the pytorch-lightning supported loggers ``` !pip install wandb from pytorch_lightning.loggers import WandbLogger wandb_logger = WandbLogger(project="simplet5") ``` ``` from simplet5...

Shivanand Roy

ValueError: text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples).

ValueError: text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples).

Unicode Charecter training issue

ValueError: transformers.spec is None

Metrics and logging.

Metrics and logging.

Add LongT5 support

Would this work to train flan-t5-xxl on multiple GPUs?

Would this work to train flan-t5-xxl on multiple GPUs?

Fine Tune model for other languages