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.

coreml/config.json

@@ -12,8 +12,6 @@
     {
       "file": "pp_ocrv6_coreml_int8.pte",
       "precision": "int8",
-      "quantized": true,
-      "default": true,
       "size_bytes": 8269910,
       "methods": {
         "detect": {

vulkan/config.json

@@ -12,8 +12,6 @@
     {
       "file": "pp_ocrv6_vulkan_fp16.pte",
       "precision": "fp16",
-      "quantized": false,
-      "default": true,
       "size_bytes": 26176856,
       "methods": {
         "detect": {

xnnpack/config.json

@@ -12,8 +12,6 @@
     {
       "file": "pp_ocrv6_xnnpack_fp32.pte",
       "precision": "fp32",
-      "quantized": false,
-      "default": true,
       "size_bytes": 31066200,
       "methods": {
         "detect": {
@@ -68,8 +66,6 @@
     {
       "file": "pp_ocrv6_xnnpack_int8.pte",
       "precision": "int8",
-      "quantized": true,
-      "default": true,
       "size_bytes": 23890904,
       "methods": {
         "detect": {