Fix config schema and document XNNPACK int8 quality

README.md

@@ -23,17 +23,37 @@ revision `5426e4f0f36572d16453bbda7a8389317b1bef99`.
 | `small/coreml/depth_anything_v2_small_coreml_fp16.pte` | coreml | fp16 |
 | `small/vulkan/depth_anything_v2_small_vulkan_fp16.pte` | vulkan | fp16 |
 
+## XNNPACK int8
+
+The INT8 export uses dynamic INT8 activations and per-channel INT8 weights for
+linear layers; convolutions remain floating point. Public inputs and outputs
+remain float32.
+
+Numerical agreement with the float reference on four held-out upstream example
+illustrations (`demo17`–`demo20`):
+
+| Image | Range-normalized RMSE | Correlation |
+| --- | --- | --- |
+| demo17 | 1.24% | 0.999633 |
+| demo18 | 1.34% | 0.999104 |
+| demo19 | 0.47% | 0.999970 |
+| demo20 | 1.28% | 0.999690 |
+
+Range-normalized RMSE is RMSE divided by the reference depth range. These are
+numerical export checks, not depth-accuracy benchmarks. A synthetic random-input
+check reached 3.32% range-normalized RMSE (correlation 0.990703).
+
 ## Repository structure
 
 ```
-config.json                                                   39 B
-small/coreml/config.json                                      928 B
-small/coreml/depth_anything_v2_small_coreml_fp16.pte          50.2 MB
-small/vulkan/config.json                                      928 B
-small/vulkan/depth_anything_v2_small_vulkan_fp16.pte          49.6 MB
-small/xnnpack/config.json                                     1.6 kB
-small/xnnpack/depth_anything_v2_small_xnnpack_fp32.pte        99.0 MB
-small/xnnpack/depth_anything_v2_small_xnnpack_int8.pte        35.5 MB
+config.json                                              39 B
+small/coreml/config.json                                 879 B
+small/coreml/depth_anything_v2_small_coreml_fp16.pte     50.2 MB
+small/vulkan/config.json                                 879 B
+small/vulkan/depth_anything_v2_small_vulkan_fp16.pte     49.6 MB
+small/xnnpack/config.json                                1.5 kB
+small/xnnpack/depth_anything_v2_small_xnnpack_fp32.pte   99.0 MB
+small/xnnpack/depth_anything_v2_small_xnnpack_int8.pte   35.5 MB
 ```
 
 ## Compatibility

small/coreml/config.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
   "model": "depth_anything_v2_small",
-  "family": "depth-anything-v2",
+  "family": "depth_anything_v2",
   "capabilities": [
     "depth-estimation"
   ],
@@ -11,8 +11,6 @@
     {
       "file": "depth_anything_v2_small_coreml_fp16.pte",
       "precision": "fp16",
-      "quantized": false,
-      "default": true,
       "methods": {
         "forward": {
           "inputs": [

small/vulkan/config.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
   "model": "depth_anything_v2_small",
-  "family": "depth-anything-v2",
+  "family": "depth_anything_v2",
   "capabilities": [
     "depth-estimation"
   ],
@@ -11,8 +11,6 @@
     {
       "file": "depth_anything_v2_small_vulkan_fp16.pte",
       "precision": "fp16",
-      "quantized": false,
-      "default": true,
       "methods": {
         "forward": {
           "inputs": [

small/xnnpack/config.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
   "model": "depth_anything_v2_small",
-  "family": "depth-anything-v2",
+  "family": "depth_anything_v2",
   "capabilities": [
     "depth-estimation"
   ],
@@ -11,8 +11,6 @@
     {
       "file": "depth_anything_v2_small_xnnpack_fp32.pte",
       "precision": "fp32",
-      "quantized": false,
-      "default": true,
       "methods": {
         "forward": {
           "inputs": [
@@ -42,8 +40,6 @@
     {
       "file": "depth_anything_v2_small_xnnpack_int8.pte",
       "precision": "int8",
-      "quantized": true,
-      "default": false,
       "methods": {
         "forward": {
           "inputs": [