Update README.md
Browse files
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:
|