wassname/peft
1
0
Fork 0
mirror of https://github.com/wassname/peft.git synced 2026-09-10 12:20:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Sourab Mangrulkar
2023-01-04 20:15:37 +05:30
parent c8d3def60e
commit 61c577fc4e
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -61,13 +61,13 @@ So, we are already seeing comparable performance to SoTA with parameter effcient
### Parameter Efficient Tuning of Diffusion Models
GPU memory and training times required by different settings during training are given below. The final checkpoint size being `8.8 MB`.
GPU memory required by different settings during training are given below. The final checkpoint size being `8.8 MB`.
Hardware: Single A100 80GB GPU with CPU RAM above 64G
| Model | Full Finetuning | PET-LoRA |
| --------- | ---- | ---- |
| CompVis/stable-diffusion-v1-4 | 27.5GB GPU / 3.97GB CPU / 22 minutes | 15.5GB GPU / 3.84GB CPU / 5.5 minutes |
| CompVis/stable-diffusion-v1-4 | 27.5GB GPU / 3.97GB CPU | 15.5GB GPU / 3.84GB CPU |
**Training**