ggml : remove q1_3 and q2_2

* llama : remove the separate scale tensors of BitNet b1.58

They won't be needed, since the remaining ternary quant types have
built-in scales.

ggml/include/ggml.h

@@ -392,8 +392,6 @@ extern "C" {
         GGML_TYPE_Q4_0_8_8 = 33,
         GGML_TYPE_TQ1_0   = 34,
         GGML_TYPE_TQ2_0   = 35,
-        GGML_TYPE_Q2_2    = 36,
-        GGML_TYPE_Q1_3    = 37,
         GGML_TYPE_COUNT,
     };