Add the missing coreml/config.json; drop the image fp32 variant

model.json points at {backend}/config.json, but this repo had no coreml/config.json at all, so the Core ML artifacts were published without a contract. Added, following the same shape as the published xnnpack config: a single variant with `components` mapping the image and text towers to their files.

The image fp32 variant is removed. Its text counterpart was already dropped, so the pair was mismatched, and fp16 is equivalent: relative L2 0.0026 and cosine 0.999997 against fp32 across 8 images. Core ML fp32 also cannot run on the ANE and measured slower everywhere.

Note the Core ML text tower takes two inputs (ids and mask) at [1,74] where the xnnpack text tower takes one at [1,77]; that difference is pre-existing and preserved here.

v0.9.0 and below are untouched.

coreml/clip_vit_base_patch32_image_coreml_fp32.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:764f2ed8c91204d27f7c7679acdf074b6c118b7e51b1fd71fef995447f8a8594
-size 351813648

coreml/config.json

@@ -0,0 +1,75 @@
+{
+  "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
+  "model": "clip_vit_base_patch32",
+  "family": "clip",
+  "capabilities": [
+    "text-embedding",
+    "image-embedding"
+  ],
+  "backend": "coreml",
+  "license": "mit",
+  "tokenizer": "../tokenizer.json",
+  "variants": [
+    {
+      "file": null,
+      "components": {
+        "image": "clip_vit_base_patch32_image_coreml_fp16.pte",
+        "text": "clip_vit_base_patch32_text_coreml_fp16.pte"
+      },
+      "precision": "fp16",
+      "quantized": false,
+      "default": true,
+      "methods": {
+        "image": {
+          "inputs": [
+            {
+              "shape": [
+                1,
+                3,
+                224,
+                224
+              ],
+              "dtype": "float32"
+            }
+          ],
+          "outputs": [
+            {
+              "shape": [
+                1,
+                512
+              ],
+              "dtype": "float32"
+            }
+          ]
+        },
+        "text": {
+          "inputs": [
+            {
+              "shape": [
+                1,
+                74
+              ],
+              "dtype": "int64"
+            },
+            {
+              "shape": [
+                1,
+                74
+              ],
+              "dtype": "int64"
+            }
+          ],
+          "outputs": [
+            {
+              "shape": [
+                1,
+                512
+              ],
+              "dtype": "float32"
+            }
+          ]
+        }
+      }
+    }
+  ]
+}