Releases: alibaba/graph-gpt
Releases · alibaba/graph-gpt
v0.3.1
v0.3.1
Model
- Add drop path to regularize large models, and it works quite well for deep models
- Add EMA
Other
- Add one package dependency:
timm
, to implement EMA - Update README to include details of Eulerian sequence and cyclic node re-index.
- Code refactoring.
- Tokenization config json refactoring.
- Update vocab by adding some special tokens, e.g.,
<bos>
,<new>
,<mask>
and etc. - Turn of optimizer offload in deepspeed config to boost the training speed.
v0.3.0
v0.2.1
implement permute nodes and refactor codes
v0.2.0 implement permute nodes and refactor codes
initial release with common-io bug fixed
v0.1.1 remove package common-io dependence because it is only used in Alibab…