 Kai Wu
|
41a46d811d
fix alpaca dataset by using 5% of the data as eval and make sure len((eval_loader)>0
|
hai 1 ano |
 exhyy
|
69db75d425
fix incorrect split of InstructionDataset
|
hai 1 ano |
 Matthias Reso
|
fe8122daf1
Adapt alpaca dataset to ConcatDataset
|
hai 1 ano |
|
Matthias Reso
|
d3015b4c80
Remove max_word from alpaca; lets deal tokenizer deal with truncation
|
hai 1 ano |
|
Matthias Reso
|
be63d9ec39
Remove padding in alpaca ds; remove concat in grammar
|
%!s(int64=2) %!d(string=hai) anos |
|
Matthias Reso
|
cf678b9bf0
Adjust imports to package structure + cleaned up imports
|
%!s(int64=2) %!d(string=hai) anos |
|
Matthias Reso
|
4c9cc7d223
Move modules into separate src folder
|
%!s(int64=2) %!d(string=hai) anos |
