'diffusion-typo-change'

This commit is contained in:
ziyuhuang123 2022-12-22 10:28:59 +08:00
parent 622f863291
commit cf5028363c

View File

@ -104,7 +104,7 @@ You can change the trainging config in the yaml file
- max_epochs: max training epochs - max_epochs: max training epochs
- precision: usefp16 for training or not, default 16, you must use fp16 if you want to apply colossalai - precision: usefp16 for training or not, default 16, you must use fp16 if you want to apply colossalai
## Finetone Example ## Finetune Example
### Training on Teyvat Datasets ### Training on Teyvat Datasets
We provide the finetuning example on [Teyvat](https://huggingface.co/datasets/Fazzie/Teyvat) dataset, which is create by BLIP generated captions. We provide the finetuning example on [Teyvat](https://huggingface.co/datasets/Fazzie/Teyvat) dataset, which is create by BLIP generated captions.