Suraj Patil

Not sure if it's related to dataset (.parquet format). Could you please post the code snippet you used to launch the script ? Thanks.

Hi @AlafateABULIMITI Yes, we are considering adding this model. But since this is a complex model it might take a couple of weeks to fully integrate it.

Thank you for sharing this @Darth-Carrotpie

I have started working on it. Should have a PR soon!

Thank you @zolekode . For training in other languages we'll need a pre-trained model and dataset in that language. I'm not sure if there are pre-trained seq-to-seq models available for...

Hi @hunkim , I do want to add support for GPT-2 in a week or two. Do you think you can upload this model on HF model hub so that...

@hunkim , @ghost, @zolekode , @epetros, @overnightJustifier mT5 has just been added to transformers, so now you can use it to fine-tune on your own language if mT5 supports it....

That argument is needed for the `xla_spawn` [script](https://github.com/huggingface/transformers/blob/master/examples/xla_spawn.py) to launch training on TPU. It loads the training script and launches it on the tpu cores. If I'am not wrong, these...

Hi @Deepayan137 What is your `nlp` version ? I've only tested it with `0.2.0 `. Also I would make sure if I passed the correct path to `run_qg`. And I...

Hey, @Deepayan137 sorry for responding late. Were you able to resolve this ?