Manuel de Prada Corral

> Before the appearance of this error, there were some other problems that could be fixed. This problem occurs when trying to retrain some other T5 models [output (3).txt](https://github.com/manueldeprada/Pretraining-T5-PyTorch-Lightning/files/13450651/output.3.txt) It...

Probably this is the issue: https://github.com/manueldeprada/Pretraining-T5-PyTorch-Lightning/blob/1c24be36ec77b22c74fc956ff2728e71db374d91/prepare_dataset.py#L115 Can you change it to be the class of your model or AutoTokenizer and check if it works?

Hi, cord19-standard.txt is a plaintext file with a sentence per line. You can have a look for a month in the following link: https://nubeusc-my.sharepoint.com/:f:/g/personal/manuel_deprada_rai_usc_es/Ehl8gWaHa_tPs7rOPBZncGABiEE84D7zRxdlzRyvK9as5A?e=Rt0pve The preprocessed data, is stored in...

Sorry for the delay, I didn't correctly receive the notification. If I don't answer you can reach out to me by email. > Hello, > > Thank you so much...

metada.csv is a file included with the official CORD-19 dataset. hope it helps!

just search in the folder for all *.mp3 files and then cut paste them to other folder

> I fixed this by changing in the pair.rs https://jitstreamer.com to http://jitstreamer.com and it fixed the issue Worked for me! I leave here the binary for anyone too lazy to...

Some of us are also trying to get out of TikTok-like "endless scroll" video feature, it would be very nice that this feature is considered

Clone the repo, execute: g++ -std=c++11 -pthread -O3 fastBPE/main.cc -IfastBPE -o fast pip install ./ Working on python 3.12, fedora linux.

I add some things I noticed, in case its helpful: 1. The issue does not occur the first time zellij is launched. Removing ~/.cache/zellij solves the issue for the next...