TemporalMesh Transformer: 29.4 PPL at 48% compute — dynamic graph attention + adaptive exit gates (open-source)
🔥 1
#30 opened 5 months ago
by 
vigneshwar234
TemporalMesh Transformer: 29.4 PPL at 48% compute — dynamic graph attention + adaptive exit gates (open-source)
#29 opened 5 months ago
by vigneshwar234
Delete plain_text/train-00025-of-00080.parquet
#27 opened 8 months ago
by 
steferyang
resonancenet
#26 opened 8 months ago
by 
kristian5013
trojan infections in data sets
#25 opened about 1 year ago
by 
JayRhino
Problem loading dataset script
3
#21 opened over 1 year ago
by 
Ohamine
Upload dataset (part 00001-of-00002)
#20 opened about 2 years ago
by 
Skylion007
Upload dataset (part 00000-of-00002)
#19 opened about 2 years ago
by Skylion007
convert-parquet-full
3
#18 opened about 2 years ago
by Skylion007
whats the most anyone has trainined this dataset what was the best loss they reached
1
#17 opened about 2 years ago
by 
sahil26k
I meet with a problem unable to download the openwebtext dataset
4
#16 opened about 2 years ago
by 
zhuoran-li
Update openwebtext.py with trust_remote_code
#14 opened over 2 years ago
by 
nnp2923
Dataset Viewer issue: DatasetWithScriptNotSupportedError
2
#13 opened over 2 years ago
by 
Lhouss
Notifications from parquet-converter
2
#11 opened about 3 years ago
by 
parquet-converter
hello, how to convert these dataset to .bin and .idx to train gpt2?
2
#8 opened over 3 years ago
by 
etoilestar
🚩 Report: file marked as unsafe
5
#6 opened over 3 years ago
by 
afmck
How can I convert this dataset
#4 opened over 3 years ago
by 
luciferxf
Processing of the data
1
#1 opened about 4 years ago
by 
IdoAmit198