Ucas-HaoranWei/Vary-tiny-600k
Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)
Python
Issues
- 0
About the BERT model you used
#5 opened by Coobiw - 2
- 1
Training met nan loss in second epoch. Why?
#2 opened by white2018 - 0
Train on persian and urdu
#4 opened by MohamedLahmeri01 - 6
inference error
#1 opened by white2018