huggingface / huggingface/open-muse
Test out hyperparameters in paper
Open
- Dominant language
- Python
- Stars
- 359
- Forks
- 30
- PR merge metrics
- No merged PRs in 30d
Description
I noticed that our current training hyper parameters for the base model is similar to the hyper parameters for the super-resolution model. Instead of the base one(hidden size 1024 vs 2048) so might be interesting trying out with the default parameters too
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.