Clémentine Fourrier
Clémentine Fourrier
Completely missed this conversation! (better late than never I guess? ^^") Yes, my point was mostly wrt I/O, to constrain user selections - I remember, for ex, having seen tasks...
Hi @LyuLumos ! I'm in a rush at the moment, but I will investigate this at the end of the month !
Hi @daeyeoplee ! Can you send me your logs?
Hm, this is the first time such an error is reported. If you are absolutely certain you are launching your notebook with the correct values (which you can test my...
Hi! Thank you for your message :) This is linked to two issues: - when we can't get a number of parameters from the hub or the model name, we...
Hi! Evaluation is notoriously fickle and prompt sensitive. To reproduce Meta's number, you would need to run the exact same setup (same batch size, same generation temperature, same few-shot samples...
Ping me if you need help! :smile:
Ok so you will need to do something similar to this: ```python import argparse import os, sys from pathlib import Path import torch from torch import nn from torch.hub import...
Hi @Raman-Kumar! I don't think the tensorflow error is very important atm, don't worry :smile: Here is my argument list: `--checkpoint_name Name_of_the_checkpoint_you_downloaded_for_tokenGT --pytorch_dump_folder_path tmp --user-dir "Directory where you cloned the...
I think you read the error correctly, apparently for TokenGT+fairseq it does not seem to be. You could try passing it as `False` (I think it's a boolean), or looking...