gmongaras commited on
Commit
f6f93f5
·
verified ·
1 Parent(s): 91a4be0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -15,4 +15,4 @@ Checkpoints from training a model with:
15
  - a batch size of 70 (I think) with 2 accumulation steps
16
  - using flash attention
17
  - RoPEV2 (something I was experimenting with)
18
- - 256x256 resolution
 
15
  - a batch size of 70 (I think) with 2 accumulation steps
16
  - using flash attention
17
  - RoPEV2 (something I was experimenting with)
18
+ - 256x256 max resolution (but any multiple of 16 up to 256x256 works)