Core ML: pin compute_unit=CPU_ONLY, drop the fp32 variant

These graphs fail the Apple Neural Engine path (coremltools#2825 masked mean-pool over a dynamic sequence dim; clip-text additionally ANECCompile FAILED). Core ML still returned correct output because it silently fell back to CPU, but the failed ANE compile was paid on every call. Pinning compute_unit=CPU_ONLY skips the attempt.

Measured on an iPhone 16, fp16, 3 warmup + 15 timed runs, median:
all-MiniLM 13.7 ms -> 2.5 ms 5.5x
multi-qa 14.1 ms -> 2.5 ms 5.6x
paraphrase-L12 26.9 ms -> 4.2 ms 6.4x
distiluse 33.0 ms -> 8.0 ms 4.1x
clip-text 18.1 ms -> 4.9 ms 3.7x

The fp32 variant is removed. Once fp16 is pinned it is dominated on both axes: slower (all-MiniLM 4.5 vs 2.5 ms, clip-text 9.5 vs 4.9 ms) and twice the size. Output fidelity against fp32 was gated first: relative L2 4e-6 (all-MiniLM, multi-qa), 0.0010 (paraphrase), 0.0046 (distiluse).

v0.9.0 and below are untouched.

coreml/config.json

@@ -1,18 +1,16 @@
 {
   "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
   "model": "paraphrase_multilingual_minilm_l12_v2",
-  "family": "minilm",
+  "family": "sbert",
   "capabilities": [
     "text-embedding"
   ],
   "backend": "coreml",
   "license": "apache-2.0",
-  "tokenizer": "../tokenizer.json",
-  "tokenizer_config": "../tokenizer_config.json",
   "variants": [
     {
-      "file": "paraphrase_multilingual_minilm_l12_v2_coreml_fp32.pte",
-      "precision": "fp32",
+      "file": "paraphrase_multilingual_minilm_l12_v2_coreml_fp16.pte",
+      "precision": "fp16",
       "quantized": false,
       "default": true,
       "methods": {
@@ -21,35 +19,14 @@
             {
               "shape": [
                 1,
-                -1
+                126
               ],
               "dtype": "int64"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                384
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      }
-    },
-    {
-      "file": "paraphrase_multilingual_minilm_l12_v2_coreml_fp16.pte",
-      "precision": "fp16",
-      "quantized": false,
-      "default": false,
-      "methods": {
-        "forward": {
-          "inputs": [
+            },
             {
               "shape": [
                 1,
-                -1
+                126
               ],
               "dtype": "int64"
             }
@@ -67,4 +44,4 @@
       }
     }
   ]
-}
+}

coreml/paraphrase_multilingual_minilm_l12_v2_coreml_fp16.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da57435320e06764b5f479e9d44b99e663d5a8d45a5b0cf3742d07e36bbcf873
+oid sha256:ffec84b4e357bc843d65dcc612158d7883b19e7f533c15dd6e6c57d853d9f1ac
 size 235565340

coreml/paraphrase_multilingual_minilm_l12_v2_coreml_fp32.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fd7e80c15a7cc5c905c9f5db232aeb742ef6054d7af05947113e25db34317354
-size 470488106