From ed48331cf3f943eccf10b1311862bd377f6712dc Mon Sep 17 00:00:00 2001 From: Ronald Tse Date: Tue, 25 Aug 2026 21:01:57 +0800 Subject: [PATCH] release: ara-diac-small-1.0-int8 (int8, parity cer_delta 0.0pp on 800 samples) --- models.yaml | 13 +++++++ .../ara-diac-small-1.0-int8.metadata.yaml | 36 +++++++++++++++++++ 2 files changed, 49 insertions(+) create mode 100644 models/ara-diac-small-1.0/ara-diac-small-1.0-int8.metadata.yaml diff --git a/models.yaml b/models.yaml index 1193bbe..6671eae 100644 --- a/models.yaml +++ b/models.yaml @@ -202,3 +202,16 @@ models: - {name: der_morph_greedy, value: 1.5317, source: rababa/docs/RESULTS.md#r6-verdict-table-sadeeddiac-25-2026-08-21} parity: {samples: 500, cer_delta: 0.0} license: BSD-3-Clause + ara-diac-small-1.0-int8: + task: diacritization + scripts: [Arab, Arab] + precision: int8 + filename: ara-diac-small-1.0-int8.zip + url: https://github.com/interscript/interscript-ml/releases/download/ara-diac-small-1.0/ara-diac-small-1.0-int8.zip + sha256: af247d837bee7e755b5287102cfb715c48dc90c2cf41ec1c41e7238e1a72b678 + size: 256959713 + metrics: + - {name: der_teacher_greedy, value: 1.3205, source: interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0} + - {name: der_student_greedy, value: 3.658, source: interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0} + parity: {samples: 800, cer_delta: 0.0} + license: BSD-3-Clause diff --git a/models/ara-diac-small-1.0/ara-diac-small-1.0-int8.metadata.yaml b/models/ara-diac-small-1.0/ara-diac-small-1.0-int8.metadata.yaml new file mode 100644 index 0000000..20ab56f --- /dev/null +++ b/models/ara-diac-small-1.0/ara-diac-small-1.0-int8.metadata.yaml @@ -0,0 +1,36 @@ +format: imf-v1 +id: ara-diac-small-1.0 +task: diacritization +source_script: Arab +target: Arab +tokenizer: bytes +opset: 14 +decoder: kv +precision: int8 +license: BSD-3-Clause +trained_from: 'sequence-level KD from the r6 teacher (rababa_arabic_byt5/run-006-morph/best, + 2.5793 windowed DER-CE on the full SadeedDiac-25 protocol): 29,322 greedy teacher-generated + labels on the r5-units corpus (domain + replay, 1400-byte windows); ByT5-small init + google/byt5-small; 3 epochs; checkpoint rababa-checkpoints:/rababa_arabic_distill_small/run-002/best. + Client tier: capacity-limited at +2.34pp over the teacher — the strict gate is met + by the teacher release (ara-diac-1.0); shipped as the Arabic client rung per the + documented Thai precedent.' +metrics: +- name: der_teacher_greedy + value: 1.3205 + protocol: windowed DER-CE (1400-byte windows, word-boundary split, greedy, haraqat-projected, + Misraj evaluator); 300 SadeedDiac-25 paragraphs; r6 teacher on the same harness + as the student + source: interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0 +- name: der_student_greedy + value: 3.658 + protocol: same harness; +2.34pp client-tier shrink cost (strict gate was teacher + +0.5pp); shipped capacity-limited — see the RESULTS gate discussion + source: interscript/interscript-ml docs/RESULTS.md#ara-diac-small-1.0 +parity: + samples: 800 + cer_delta: 0.0 +sha256: + decoder-kv.onnx: 657cd4181dda3812c3fd0fce0048c3b36df46b59a05f5ee6234c6ea2deea1e46 + decoder.onnx: c3f67a6ba51ef2a9ccb1eaea1f47c5bd097fde4b4341c0adbf439c43acdf9065 + encoder.onnx: 311532c232476969476f9cfbcfa72f00ee7d35279728f575a47f44baff3fc7d2