gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)

shg8 · Apr 27, 2024 · ccdc5e1 · ccdc5e1
1 parent d3c0f42
commit ccdc5e1
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
@@ -872,6 +872,7 @@ def get_type(val: Any) -> GGUFValueType:
     GGMLQuantizationType.I32:     (1, 4),
     GGMLQuantizationType.I64:     (1, 8),
     GGMLQuantizationType.F64:     (1, 8),
+    GGMLQuantizationType.IQ1_M:   (256, QK_K // 8 + QK_K // 16  + QK_K // 32),
 }