Reza2kn/Bina-0.4-Koochik-CoreML-INT4

Bina 0.4 Koochik — CoreML-INT4

Calibration-aware 4-bit derivative of Reza2kn/Bina-0.4-Koochik, using checkpoint 18,404. The architecture and 630,800,496 unique parameters are unchanged. Original training was not modified.

170 linear weight matrices use symmetric GPTQ codes with group size 32 and FP32 group scales, calibrated on 64 approved training-only regions with fresh 18,404 source sequences. Tied input/output embeddings, convolutions, positions, norms, biases and unused auxiliary heads keep higher precision. “4-bit” describes those linear codes, not every stored parameter or activation. The canonical packed candidate is 533,891,055 bytes, about 6.771 effective bits per original parameter including higher precision exceptions and serialization; this runtime package has a different footprint, including separate components and any duplicated tables. No native BitNet or universal speed claim is made.

Validation

Actual target-runtime results on the frozen 64-image / 14,127-source-character qualification set, using the included pixel-layout-v2 pipeline:

Runtime	Corrected source character parity	Original whole-page parity	New caps / repetition flags
coreml	98.9028%	97.4063%	0 / 0

Character agreement is 1 - pooled NFC Levenshtein edits / pooled NFC source characters, unclipped. The corrected source is the immutable uncompressed BF16 cast of the original checkpoint, run on the same pixel regions with source decoding. Original whole-page results are reported separately. These are source agreement measurements, not human-annotated OCR accuracy, per-image guarantees, or an independent unseen OCR benchmark. The final set was used for runtime qualification, not quant fitting or candidate selection. Calibration and final source groups are disjoint.

Greedy decoding uses repetition penalty 1.1, at most 2,048 tokens per region and the source's at-most-one resolution retry. No passage-stopping guard, no-repeat constraint, output deduplication or hidden truncation improves these scores. Token caps and repetition are audited. The pixel-only layout covers all original pixels once. Small decorative text, logos, handwriting and complex layouts can still differ. Markup mode is available but was not separately corpus-qualified.

Tested with CoreML Tools 9.0, CPU_AND_GPU, on an Apple M2 Mac. Packages target macOS 15 / iOS 18 or later and use FP32 arithmetic with compressed INT4 linear weights. iPhone/iPad deployment, ANE execution and mobile performance have not been measured. This is a model-specific split pipeline; use the included preprocessing and cached decoder.

Use

The complete runtime download is approximately 1,106.2 MB (decimal), including higher precision exceptions, split components, tokenizer/position assets and runtime files. INT4 does not mean every parameter or activation is four bits.

Download this complete repo, including external model data, then run:

python -m pip install -r requirements.txt
python run_ocr.py --format coreml --image examples/demo.png --output result.json

The demo is newly authored synthetic text. Its independent-folder installation smoke reached natural EOS and transcribed both lines exactly. The private user letter, training examples and protected qualification images/transcriptions are not included. validation/character-parity.json contains aggregate evidence. artifact-manifest.json lists release hashes.

Source and license

The standalone parent contains the original FP32 checkpoint weights and complete upstream provenance. This derivative inherits OpenMDW 1.1; preserve LICENSE and third-party notices. See quantization.json for source/candidate hashes. Parent architecture: NVIDIA Nemotron-3.5-Parse. The binary/runtime versions and arithmetic profiles are part of the qualification; changing them requires another check.

Local latency diagnostic

On the same newly authored400x104 PNG (34 generated tokens) on an Apple M2 Mac, the supplied loader settings produced warm median end-to-end times of coreml: 0.827 s across three real repeated generations. Only one inference process was active; normal desktop apps and the idle resident browser could remain present. These short-demo numbers are not corpus throughput, mobile measurements or a universal speed claim. See validation/latency-demo-*.json.