ovedrive commited on
Commit
b4359c8
·
verified ·
1 Parent(s): afb9d81

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -19,7 +19,14 @@ base_model_relation: quantized
19
 
20
  Ovedrive version of mixed precision targetting 12GB VRAM or less than. It is not widely tested, please do share your results and optimal steps.
21
 
22
- thank you https://justlab.ai for the GPUs
 
 
 
 
 
 
 
23
 
24
  ## Quick Start
25
 
 
19
 
20
  Ovedrive version of mixed precision targetting 12GB VRAM or less than. It is not widely tested, please do share your results and optimal steps.
21
 
22
+ thank you [Justlab.ai](https://Justlab.ai) for the GPUs
23
+
24
+ Steps 20, CFG 4 for both (random seed)
25
+ | Original ERNIE-Image | Ovedrive NF4 quantized |
26
+ |---|---|
27
+ | ![Original ERNIE-Image output](./fullmodel.webp) | ![Ovedrive ERNIE-Image NF4 output](./ovedrive.webp) |
28
+ | Full precision baseline | Mixed precision NF4 |
29
+
30
 
31
  ## Quick Start
32