Initial int4 v0.1.0 bundle

.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

MANIFEST.json

@@ -0,0 +1,12 @@
+{
+  "name": "privacy-filter-int4-v0.1.0",
+  "version": "0.1.0",
+  "variant": "int4",
+  "files": {
+    "weights.safetensors": "c2b21e76d88c16239f512d5f9b7c36468ed331c892dafab4c3281d870e361ec8",
+    "tokenizer.json": "0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3",
+    "tokenizer_config.json": "6c14af9ce1a284d3c3c5146b26efe4cd589c68e1dd4e9d94455606ec911ba774",
+    "id2label.json": "82ec14dd6f97ce46c227689a06507f258919e48235591a90bfc1cb73f97f5a32",
+    "model_config.json": "db5c0180d6e454987f207ccc00dfc1ceb5f710b0d43a3113d090e5d3cf640b87"
+  }
+}

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: openai/privacy-filter
+tags:
+  - mlx
+  - token-classification
+  - privacy
+  - pii-detection
+  - bioes
+library_name: mlx
+pipeline_tag: token-classification
+---
+
+# privacy-filter-mlx (int4)
+
+MLX-converted, int4-quantized weights of [openai/privacy-filter](https://huggingface.co/openai/privacy-filter),
+packaged for use with [PrivacyFilterKit](https://github.com/kokluch/privacy-filter-swift) — a Swift package
+that runs on-device PII detection on Apple platforms via [MLX-Swift](https://github.com/ml-explore/mlx-swift).
+
+## Bundle contents
+
+| File | Purpose |
+|------|---------|
+| `weights.safetensors` | int4 affine-quantized weights (group_size=64). Embedding + classifier head kept full-precision. |
+| `tokenizer.json` | Hugging Face tokenizer (copied verbatim from upstream). |
+| `tokenizer_config.json` | Tokenizer config. |
+| `id2label.json` | 33-label BIOES table (8 entity types: account_number, private_address, private_date, private_email, private_person, private_phone, private_url, secret). |
+| `model_config.json` | Architecture parameters consumed by the Swift runtime. |
+| `MANIFEST.json` | SHA-256 hashes of every file in the bundle. |
+
+## Architecture
+
+- 8 transformer layers, hidden size 640, 14 attention heads (2 KV heads, GQA)
+- 128 local experts, top-4 MoE routing
+- 200 064 vocab, 131 072 max position embeddings, sliding-window attention (128)
+- 33-label BIOES head; the Swift decoder derives a BIOES validity mask at runtime
+  (no learned CRF transition matrix in the upstream checkpoint)
+
+## Usage (Swift)
+
+```swift
+import PrivacyFilterKit
+
+let bundle = URL(fileURLWithPath: "/path/to/privacy-filter-int4-v0.1.0")
+let filter = try await PrivacyFilter(source: .directory(bundle))
+let entities = try await filter.detect(in: "Email me at jane@example.com")
+```
+
+See the [PrivacyFilterKit README](https://github.com/kokluch/privacy-filter-swift) for the full API.
+
+## Conversion pipeline
+
+The conversion was produced by the scripts in [`privacy-filter-swift/scripts/`](https://github.com/kokluch/privacy-filter-swift/tree/main/scripts):
+
+1. `01_download_hf.py` — download the upstream checkpoint
+2. `02_export_config.py` — extract label table, tokenizer, normalized model config
+3. `03_convert_mlx.py` — rename keys, downcast to bf16, write MLX-friendly safetensors
+4. `04_quantize_mlx.py` — int4 affine quantization (embedding + classifier head full-precision)
+5. `06_export_bundle.py` — assemble bundle + MANIFEST + tar.gz archive
+
+## License
+
+Apache 2.0, inherited from the upstream model. See [LICENSE](https://www.apache.org/licenses/LICENSE-2.0.txt).
+
+## Modifications from upstream
+
+This bundle is a derivative of `openai/privacy-filter`. Significant changes:
+
+- Weights converted from PyTorch safetensors to MLX-format safetensors (key rename + bf16 cast).
+- int4 affine-quantized (group_size=64). Embedding, classifier head, and any transition matrix
+  are kept full-precision.
+- Bundle adds `model_config.json`, `id2label.json`, and `MANIFEST.json` for the Swift runtime;
+  no model logic is changed.
+
+## Credits
+
+- Upstream model: [`openai/privacy-filter`](https://huggingface.co/openai/privacy-filter)
+- Swift runtime: [PrivacyFilterKit](https://github.com/kokluch/privacy-filter-swift)
+- Conversion runtime: [MLX](https://github.com/ml-explore/mlx) / [MLX-Swift](https://github.com/ml-explore/mlx-swift)

id2label.json

@@ -0,0 +1,35 @@
+{
+  "0": "O",
+  "1": "B-account_number",
+  "2": "I-account_number",
+  "3": "E-account_number",
+  "4": "S-account_number",
+  "5": "B-private_address",
+  "6": "I-private_address",
+  "7": "E-private_address",
+  "8": "S-private_address",
+  "9": "B-private_date",
+  "10": "I-private_date",
+  "11": "E-private_date",
+  "12": "S-private_date",
+  "13": "B-private_email",
+  "14": "I-private_email",
+  "15": "E-private_email",
+  "16": "S-private_email",
+  "17": "B-private_person",
+  "18": "I-private_person",
+  "19": "E-private_person",
+  "20": "S-private_person",
+  "21": "B-private_phone",
+  "22": "I-private_phone",
+  "23": "E-private_phone",
+  "24": "S-private_phone",
+  "25": "B-private_url",
+  "26": "I-private_url",
+  "27": "E-private_url",
+  "28": "S-private_url",
+  "29": "B-secret",
+  "30": "I-secret",
+  "31": "E-secret",
+  "32": "S-secret"
+}

model_config.json

@@ -0,0 +1,11 @@
+{
+  "hiddenSize": 640,
+  "numLayers": 8,
+  "numAttentionHeads": 14,
+  "numKeyValueHeads": 2,
+  "numExperts": 128,
+  "topK": 4,
+  "vocabSize": 200064,
+  "maxPositionEmbeddings": 131072,
+  "numLabels": 33
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}

weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b21e76d88c16239f512d5f9b7c36468ed331c892dafab4c3281d870e361ec8
+size 971369779