metal : revert unnecessary change

Author: jhen0409

ggml-metal.metal

@@ -29,6 +29,7 @@ typedef struct {
 typedef struct {
     half d;                 // delta
     half m;                 // min
+    uint8_t qh[4];          // 5-th bit of quants
     uint8_t qs[QK5_1 / 2];  // nibbles / quants
 } block_q5_1;
 
@@ -2210,17 +2211,17 @@ void dequantize_q4_0(device const block_q4_0 *xb, short il, thread type4x4 & reg
 }
 
 template <typename type4x4>
-void dequantize_q4_1(device const block_q4_1 *xb, short il, thread type4x4 & reg) {
-    device const uint16_t * qs = ((device const uint16_t *)xb + 2);
+void dequantize_q4_0(device const block_q4_0 *xb, short il, thread type4x4 & reg) {
+    device const uint16_t * qs = ((device const uint16_t *)xb + 1);
     const float d1 = il ? (xb->d / 16.h) : xb->d;
     const float d2 = d1 / 256.f;
-    const float  m = xb->m;
+    const float md = -8.h * xb->d; // was: max / -8;
     const ushort mask0 = il ? 0x00F0 : 0x000F;
     const ushort mask1 = mask0 << 8;
 
     for (int i=0;i<8;i++) {
-        reg[i/2][2*(i%2)+0] = ((qs[i] & mask0) * d1) + m;
-        reg[i/2][2*(i%2)+1] = ((qs[i] & mask1) * d2) + m;
+        reg[i/2][2*(i%2)+0] = d1 * (qs[i] & mask0) + md;
+        reg[i/2][2*(i%2)+1] = d2 * (qs[i] & mask1) + md;
     }
 }