workfunction/McBopomofoLM-models

McBopomofoLM models (Core ML, Apple Neural Engine)

Core ML conversions of the SlothE models used by McBopomofoLM (branch lm), a fork of McBopomofo that uses the models to improve candidate selection. Both models run on the Apple Neural Engine only (computeUnits = CPU_AND_NE).

Contents

Path	What
runtime/	The exact runtime bundle shipped in McBopomofoLM v2.1.1 (Contents/Resources/SlothE): compiled .mlmodelc, embedding table, vocabularies, and runtime-manifest.txt. The app checks the size and SHA-256 of each file against the manifest before it loads that file.
mlpackage/enc25m_multi_pal2_emb.mlpackage	SlothE-T 25M encoder, 2-bit palettized. The ternary weights make this lossless. Multifunction package with functions L8/L16/L32/L64/L256. The embedding lookup runs in the caller, from runtime/enc25m_embed_f16.bin.
mlpackage/dec_mf_fp16.mlpackage	SlothE decoder pred_q35_60m (Qwen3.5 architecture), fp16. Multifunction package with functions t16/t32/t64/t96 at batch 3. Gated DeltaNet runs in fixed 16-token chunks.
scripts/	Conversion and bundling scripts, research-grade. They import helpers from the author's research workspace, which is not included, so they document the conversion and do not run on their own. MCBPMF_LM_WORK sets the workspace root.

Measured on an M2 (ANE): encoder 100% of ops on the ANE, about 0.8 ms per call. Decoder 86–95% of ops on the ANE, 2.6–7.9 ms per call depending on length.

Sources and licenses

• Weights: Luigi/sloth-ime-models, Apache-2.0.
• char2id.tsv: converted from enc/char2id.json in Luigi/slothing-web, Apache-2.0.
• Variant classes: derived from OpenCC TWVariants.txt and HKVariants.txt, Apache-2.0.
• Conversion: Apache-2.0 (LICENSE). See NOTICE.txt.