Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,10 @@ These models are made to work with [stable-diffusion.cpp](https://github.com/lee
|
|
12 |
|
13 |
Quantized using this PR https://github.com/leejet/stable-diffusion.cpp/pull/447
|
14 |
|
15 |
-
Normal K-quants are not working properly with SD3.5-Large models because around 90% of the weights are in tensors whose shape doesn't match the 256 superblock size of K-quants and therefore can't be quantized this way.
|
|
|
|
|
|
|
16 |
|
17 |
## Files:
|
18 |
|
|
|
12 |
|
13 |
Quantized using this PR https://github.com/leejet/stable-diffusion.cpp/pull/447
|
14 |
|
15 |
+
Normal K-quants are not working properly with SD3.5-Large models because around 90% of the weights are in tensors whose shape doesn't match the 256 superblock size of K-quants and therefore can't be quantized this way.
|
16 |
+
Mixing quantization types allows us to take adventage of the better fidelity of k-quants to some extent while keeping the model file size relatively small.
|
17 |
+
|
18 |
+
Only the second layers of both MLPs in each MMDiT block of SD3.5 Large models have the correct shape to be compatible with k-quants. That still makes up for about 10% of all the parameters.
|
19 |
|
20 |
## Files:
|
21 |
|