|
Download README.md from Interscript/ara-diac-layerdrop-1.0: direct link, hf CLI and curl.
- Browser
- Download file 1.45 kB
-
https://huggingface.co/Interscript/ara-diac-layerdrop-1.0/resolve/main/README.md
- Command line
-
hf download hf://Interscript/ara-diac-layerdrop-1.0/README.md
-
curl -L -o README.md https://huggingface.co/Interscript/ara-diac-layerdrop-1.0/resolve/main/README.md
1.45 kB
metadata
license: bsd-3-clause
language: ar
inference: false
tags:
- secryst
- transliteration
- diacritization
- onnx
- byt5
ara-diac-layerdrop-1.0
Part of the Secryst phonological-layer family — a dedicated model for diacritization (AR), distributed as a Secryst IMF artifact and loadable through any Secryst crystal:
from secryst import Model
Model.load("ara-diac-layerdrop-1.0")
- Artifact:
ara-diac-layerdrop-1.0-fp32.zip(0.95 GiB) - Precision variants:
ara-diac-layerdrop-1.0-int8,ara-diac-layerdrop-1.0-int4
Measured quality
Full evaluation sets, zero skipped examples, the benchmark's own evaluator. Provenance for every number is the results record of the training project.
| metric | value | provenance |
|---|---|---|
| der_teacher_fullset | 2.2921 | interscript/interscript-ml docs/RESULTS.md#layerdrop-6ep |
| der_student_fullset | 5.784 | interscript/interscript-ml docs/RESULTS.md#layerdrop-6ep |
License
BSD-3-CLAUSE
Provenance
Trained in the Secryst training monorepo and published through the interscript-ml distribution contract (models.yaml index, sha256-verified release assets, parity-gated artifacts). The canonical download channel is GitHub Releases; this repository is the Hugging Face mirror of the same bytes, pinned to the index revision.