stduhpf commited on
Commit
aa71495
·
verified ·
1 Parent(s): be70377

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -14,6 +14,8 @@ 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
 
19
  ### Mixed Types:
 
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
+ 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.
18
+
19
  ## Files:
20
 
21
  ### Mixed Types: