issues
search
bigscience-workshop
/
xmtf
Crosslingual Generalization through Multitask Finetuning
https://arxiv.org/abs/2211.01786
Apache License 2.0
516
stars
37
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Getting machine-translated prompts of xP3mt
#24
dptam
closed
1 year ago
4
Parsing the xP3 dataset
#23
hmubarak
opened
1 year ago
1
Dose mt0&bloomz trained on dev, devtest datasets of Flores-200?
#22
dsj96
closed
1 year ago
2
Export mt0-xxl-mt to ONNX fails
#21
sh0tcall3r
closed
1 year ago
2
bloomz-mt universal checkpoint
#20
LiuShixing
opened
1 year ago
2
mT0-xxl finetuning
#19
sh0tcall3r
opened
1 year ago
6
how to repreduce bloomz-*
#18
fpcsong
closed
1 year ago
6
Sync w/ paper updates
#17
Muennighoff
closed
1 year ago
0
how to convert model weights(e.g., bigscience/bloomz-560m-optimizer-states) to Hugging Face model.bin file?
#16
qazwsx042
closed
1 year ago
2
Controlled generation
#15
sh0tcall3r
opened
1 year ago
1
Use Petals without sharing GPU
#14
raihan0824
opened
1 year ago
11
Questions on creating instruction data
#13
henryhungle
opened
1 year ago
1
How to fineutne mT0 with specific down-stream data?
#12
benchen4395
opened
1 year ago
3
How to convert megatron-deepspeed checkpoints to huggingface checkpoints ?
#11
huybery
closed
1 year ago
4
Were the checkpoints selected based on the held-out performance or seen task performance?
#10
MattYoon
closed
1 year ago
2
Why does the number of templates differ between languages?
#9
MattYoon
closed
1 year ago
4
Quesiton about MTFDataset
#8
noanti
opened
1 year ago
1
I can't find the model weights that you used for experimentation.
#7
Mahyar-Ali
opened
1 year ago
1
What is the training config?
#6
mkw18
opened
1 year ago
3
Some datasets are not in xP3all
#5
mkw18
closed
1 year ago
4
P3megds URL is not available
#4
hatvn
opened
2 years ago
1
Questions about datas
#3
lbourdois
closed
1 year ago
1
Is mT0 suitable for continued training on span corruption task?
#2
junwang-wish
closed
2 years ago
2
Update README.md
#1
afaji
closed
2 years ago
0