stduhpf commited on
Commit
4ab0d85
1 Parent(s): 3b574d2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
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. 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.
 
 
 
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