MiniCheck-RoBERTa-Large Core ML (ANE) + tokenizer for MMAI faithfulness judge

MiniCheckRoBERTa.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdc1fe88ce0936308490c4a7c85d0c77c0e635132b1d83cd63dcb12a974738f
+size 276719

MiniCheckRoBERTa.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f22abc98406af87baa7d49852f3ab96fc119d37abfa5be8a811cabd989e578
+size 711795264

MiniCheckRoBERTa.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "EC56BA98-EED7-4677-9412-98AEDF446051": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "F1806992-3F3F-4330-AE25-7DF584182E93": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "EC56BA98-EED7-4677-9412-98AEDF446051"
+}

README.md

@@ -0,0 +1,33 @@
+---
+license: mit
+base_model: lytang/MiniCheck-RoBERTa-Large
+tags:
+  - coreml
+  - text-classification
+  - fact-checking
+  - grounding
+language:
+  - en
+---
+
+# MiniCheck-RoBERTa-Large — Core ML (Apple Neural Engine)
+
+Core ML conversion of [lytang/MiniCheck-RoBERTa-Large](https://huggingface.co/lytang/MiniCheck-RoBERTa-Large)
+(MIT) — a specialized grounding / fact-verification model — for in-app use on the **Apple Neural Engine**
+via Core ML. Used by Marvel Mirror AI as a claim-by-claim faithfulness judge: *does a source support a claim?*
+
+## Contents
+- `MiniCheckRoBERTa.mlpackage` — the Core ML model (fp16 weights). Inputs: `input_ids`, `attention_mask`
+  (int32, length 512). Output: `support_prob` = probability the claim is supported (class 1).
+- RoBERTa fast-tokenizer files (`tokenizer.json`, `vocab.json`, `merges.txt`, `tokenizer_config.json`,
+  `special_tokens_map.json`).
+
+## Input format
+`doc + </s> + claim`, tokenized with the RoBERTa tokenizer (`max_length` 512, padded). `support_prob > 0.5`
+= supported.
+
+## Provenance
+Converted with coremltools 9.0 (torch 2.7.0 / transformers 4.46.3), targeting CPU + Neural Engine.
+~97% of compute-bearing ops run on the ANE. Verdict-parity with the PyTorch source (max probability
+diff < 0.007); reproduces the source's full-set accuracy (21/21 fabrications caught, incl. all
+meaning- and numeric-inversions). ~60 ms/check on the ANE.

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,68 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}