t-zero

t-zero copied to clipboard

T0 (p=1) replicability

1

Hi @VictorSanh Thanks for releasing the code and data. I am trying to retrain it in pytorch Some questions , in your paper you have p=1 vs p=5.7 results Say...

tuhinjubcse

thomasw21

Missing dataset config names in P3

2

The readme says that ``For reproducibility, we have released an already cached version of the data(https://huggingface.co/datasets/bigscience/P3), which means you don't need to cache the data yourself. The only exception is...

ari9dam

ETA on pytorch training code?

4

Hope it is okay to add this as an issue - this is amazing work and would love to see the training implementation in pytorch. I see it is in...

NtaylorOX

how to use this t-zero to train my own dataset? did not find the api . if add the dataset to the cache_data_dir.I do not want reproduce. I want to use this tool train my own datasets

4

flyingwaters

reproducibility versus replicability

1

Great to see this implemented. Definitions of reproducibility and replication differ across domains, and would probably be helpful to clarify these in a few places. Happy to add these. In...

valdanchev

fine tuning on other LM models

1

Thanks for your great work！

ShiJiawenwen

"Rank classification" in evaluation for multiple choices

1

Hi, Thanks for the repo! I was wondering if you would please point out which lines of code are for the "rank classification" idea used for evaluating the multiple-choice style...

yuchenlin

Hello Maintainer of Github repo bigscience-workshop/t-zero! Thank you for your work on bigscience-workshop/t-zero. This GitHub project is interesting, and we think that it would be a great addition to make...

ijonglin