We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 1f64092 commit 9ac4b7bCopy full SHA for 9ac4b7b
quantize_weights_for_llama.cpp.ps1
@@ -81,9 +81,10 @@ ForEach ($repositoryName in $repositoryDirectories) {
81
}
82
83
84
- # We do need to compute an importance matrix for some 2-bit quantized models:
+ # We need to compute an importance matrix for all i-quants and
85
+ # small k-quants to enhance the quality of the quantum models.
86
# https://github.com/ggerganov/llama.cpp/tree/master/examples/imatrix
- $requiresImportanceMatrix = "IQ2_XXS IQ2_XS Q2_K_S".Contains($type)
87
+ $requiresImportanceMatrix = $type.Contains("IQ") -or "Q2_K Q2_K_S".Contains($type)
88
89
if ($requiresImportanceMatrix -and !(Test-Path -Path $importanceMatrixPath)) {
90
0 commit comments