ggml : fix q2_k bpw in comments (ggml/680)

diff --git a/ggml-quants.h b/ggml-quants.h
index 70c12c27465e8062f824166fb29d1a18eb7bc128..62c1df6cbd2748b9e752abf981d7b810e2b5bf24 100644 (file)
--- a/ggml-quants.h
+++ b/ggml-quants.h
@@ -70,7 +70,7 @@ static_assert(sizeof(block_q8_1) == 2*sizeof(float) + QK8_1, "wrong q8_1 block s
 // 2-bit quantization
 // weight is represented as x = a * q + b
 // 16 blocks of 16 elements each
-// Effectively 2.5625 bits per weight
+// Effectively 2.625 bits per weight
 typedef struct {
     uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits
     uint8_t qs[QK_K/4];      // quants