Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Refactoring, fixed Lora training | Volpeon | 2023-03-24 | 1 | -10/+7 |
| | |||||
* | Update | Volpeon | 2023-03-23 | 1 | -4/+4 |
| | |||||
* | Update | Volpeon | 2023-03-01 | 1 | -3/+3 |
| | |||||
* | Fixed TI normalization order | Volpeon | 2023-02-21 | 1 | -6/+5 |
| | |||||
* | Don't rely on Accelerate for gradient accumulation | Volpeon | 2023-02-21 | 1 | -6/+0 |
| | |||||
* | Remove xformers, switch to Pytorch Nightly | Volpeon | 2023-02-17 | 1 | -4/+4 |
| | |||||
* | Fix Lora memory usage | Volpeon | 2023-02-07 | 1 | -2/+0 |
| | |||||
* | Add Lora | Volpeon | 2023-02-07 | 1 | -8/+27 |
| | |||||
* | Restored LR finder | Volpeon | 2023-01-20 | 1 | -3/+1 |
| | |||||
* | Move Accelerator preparation into strategy | Volpeon | 2023-01-19 | 1 | -1/+13 |
| | |||||
* | Update | Volpeon | 2023-01-17 | 1 | -3/+2 |
| | |||||
* | Update | Volpeon | 2023-01-17 | 1 | -4/+4 |
| | |||||
* | Update | Volpeon | 2023-01-17 | 1 | -2/+8 |
| | |||||
* | Training update | Volpeon | 2023-01-16 | 1 | -3/+7 |
| | |||||
* | Handle empty validation dataset | Volpeon | 2023-01-16 | 1 | -1/+1 |
| | |||||
* | Added Dreambooth strategy | Volpeon | 2023-01-15 | 1 | -0/+183 |