Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378902ce2639de1acca4a6e1fff34b880be9ccbe960524a396e113c62156389a
+size 166537

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cd27263f9342a5246b1c56e294991e972bc201fe2b5adf389240920ddc7a88
+size 554930240

Fullstop.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "254BBDFF-3048-447B-98B6-132ECD9143E4": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "5892022E-3FFE-440D-B686-CB897CA3FDB2": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "254BBDFF-3048-447B-98B6-132ECD9143E4"
+}

README.md

@@ -0,0 +1,97 @@
+---
+license: mit
+language:
+- en
+- de
+- fr
+- it
+- nl
+- multilingual
+base_model: oliverguhr/fullstop-punctuation-multilingual-base
+pipeline_tag: token-classification
+library_name: coreml
+tags:
+- coreml
+- punctuation-restoration
+- token-classification
+- xlm-roberta
+- on-device
+---
+
+# fullstop-coreml
+
+`oliverguhr/fullstop-punctuation-multilingual-base` (XLM-RoBERTa token-classification,
+~0.3 B) converted to **CoreML** (fp16) for on-device punctuation restoration —
+downloaded on first use and run locally through CoreML + `swift-transformers`.
+
+This is a **format conversion only** — the weights are unchanged from the upstream
+PyTorch model. The model is a verbatim **token classifier**: it emits one punctuation
+label per token, so it can add punctuation (`. , ? - :`) but can never reword the
+input. Capitalization is handled separately (a heuristic restorer is typically chained
+after it).
+
+## Label map (`id2label`)
+
+| id | label | meaning |
+|----|-------|---------|
+| 0 | `""` | no punctuation |
+| 1 | `.` | period |
+| 2 | `,` | comma |
+| 3 | `?` | question mark |
+| 4 | `-` | dash |
+| 5 | `:` | colon |
+
+## Files (repo layout)
+
+The repo root is the folder a loader consumes directly:
+
+| File | Purpose |
+|------|---------|
+| `Fullstop.mlpackage/` | CoreML model bundle (compile before load) |
+| `tokenizer.json` | XLM-R Unigram tokenizer (HuggingFace `tokenizers`) |
+| `tokenizer_config.json` | tokenizer config |
+| `special_tokens_map.json` | XLM-R special tokens (`<s>`, `</s>`, `<pad>`, `<unk>`, `<mask>`) |
+| `config.json` | model config incl. `id2label` / `label2id` |
+
+## Loading (Swift)
+
+```swift
+// 1. Snapshot the repo (swift-transformers Hub):
+//    Hub.snapshot(from: Repo(id: "gregbarbosa/fullstop-coreml")) -> localDir
+// 2. Compile + load the CoreML model, build the tokenizer from the same folder:
+let compiled = try await MLModel.compileModel(at: localDir.appendingPathComponent("Fullstop.mlpackage"))
+let model = try MLModel(contentsOf: compiled)
+let tokenizer = try await AutoTokenizer.from(modelFolder: localDir)
+```
+
+Inference contract: feed `input_ids` (shape `[1, seq]`, natural length — no padding)
+and `attention_mask`; the output logits are `[1, seq, 6]` → argmax per token yields the
+label id above. Attach each **word's** punctuation from the label on its final subword
+(token boundaries marked by the XLM-R `▁` U+2581 prefix); skip special tokens.
+
+## Provenance
+
+- **Source model:** [`oliverguhr/fullstop-punctuation-multilingual-base`](https://huggingface.co/oliverguhr/fullstop-punctuation-multilingual-base) (MIT)
+- **Conversion:** PyTorch → ONNX → CoreML (fp16). Parity verified 15/15 labels identical
+  to the PyTorch reference across the conversion fixtures; tokenizer parity re-verified
+  on-device 2026-06-26.
+- **Conversion harness:** `restore-bench` (standalone repo).
+
+## License
+
+MIT — same as the upstream model. Conversion produced by Greg Barbosa.
+
+## Citation
+
+```bibtex
+@article{guhr-EtAl:2021:fullstop,
+  title={FullStop: Multilingual Deep Models for Punctuation Prediction},
+  author={Guhr, Oliver and Schumann, Anne-Kathrin and Bahrmann, Frank and B{\"o}hme, Hans Joachim},
+  booktitle={Proceedings of the Swiss Text Analytics Conference 2021},
+  month={June},
+  year={2021},
+  address={Winterthur, Switzerland},
+  publisher={CEUR Workshop Proceedings},
+  url={http://ceur-ws.org/Vol-2957/sepp_paper4.pdf}
+}
+```

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": ".",
+    "2": ",",
+    "3": "?",
+    "4": "-",
+    "5": ":"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    ",": 2,
+    "-": 4,
+    ".": 1,
+    "0": 0,
+    ":": 5,
+    "?": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_prefix_space": true,
+  "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accent": false,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}