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.

135m/xnnpack/config.json

@@ -11,8 +11,6 @@
     {
       "file": "smollm2_135m_xnnpack_8da8w.pte",
       "precision": "8da8w",
-      "quantized": true,
-      "default": true,
       "methods": {
         "enable_dynamic_shape": true,
         "forward": {

1_7b/xnnpack/config.json

@@ -11,8 +11,6 @@
     {
       "file": "smollm2_1_7b_xnnpack_8da8w.pte",
       "precision": "8da8w",
-      "quantized": true,
-      "default": true,
       "methods": {
         "enable_dynamic_shape": true,
         "forward": {

360m/xnnpack/config.json

@@ -11,8 +11,6 @@
     {
       "file": "smollm2_360m_xnnpack_8da8w.pte",
       "precision": "8da8w",
-      "quantized": true,
-      "default": true,
       "methods": {
         "enable_dynamic_shape": true,
         "forward": {