Stop restating quantized, and drop the unused default

quantized duplicated precisions.json, which is authoritative for the
quantized/non-quantized partition. default expressed a per-repository
recommendation nothing consumed: the library resolves its own per-platform
default. Both are gone from the schema.

xnnpack/config.json

@@ -11,8 +11,6 @@
     {
       "file": "phi_4_mini_xnnpack_bf16.pte",
       "precision": "bf16",
-      "quantized": false,
-      "default": true,
       "methods": {
         "enable_dynamic_shape": true,
         "forward": {
@@ -59,8 +57,6 @@
     {
       "file": "phi_4_mini_xnnpack_8da4w.pte",
       "precision": "8da4w",
-      "quantized": true,
-      "default": true,
       "methods": {
         "enable_dynamic_shape": true,
         "forward": {