Hugging Face's logo

aoiandroid
/
nllb200-coreml-256-ane-pal8

Translation
Core ML
multilingual
m2m_100
nllb
on-device
apple-silicon
neural-engine
m2m100
palettization
quantized
Model card Files
xet
 Community
nllb200-coreml-256-ane-pal8 / README.md
aoiandroid's picture
aoiandroid
Update model card (README)
d0f431b verified
preview code
|
Raw History Blame Contribute Delete
2.51 kB
metadata 
license: cc-by-nc-4.0
language:
  - multilingual
library_name: coreml
pipeline_tag: translation
base_model: facebook/nllb-200-distilled-600M
tags:
  - coreml
  - translation
  - nllb
  - on-device
  - apple-silicon
  - neural-engine
  - m2m100
  - palettization
  - quantized

NLLB-200 distilled 600M — Core ML (seq 256, ANE, palettized / pal8)

Core ML .mlpackage bundles for encoder and KV-cache decoder (init + step), exported from facebook/nllb-200-distilled-600M. Fixed sequence length 256, 8-bit palettization (pal8) on weights for a smaller footprint and Apple Neural Engine–friendly deployment.

Contents

Artifact Role
NLLB_Encoder_256.mlpackage Encode source tokens
NLLB_Decoder_256_init.mlpackage Decoder first step (no past KV)
NLLB_Decoder_256_step.mlpackage Autoregressive step with past KV
config.json Architecture metadata (seq_len, compute_units, etc.)
tokenizer/ Reference tokenizer files for the app pipeline

Companion variant

Config highlights (config.json)

  • model_type: m2m_100 / M2M100ForConditionalGeneration
  • seq_len: 256
  • ane_optimized: true
  • compute_units: CPU_AND_NE
  • Weights in the .mlpackage bundles use pal8 palettization (see Hub file sizes vs the float32 repo).

Base model and license

  • Source weights: NLLB-200 distilled 600M (Meta / FAIR).
  • Original terms are CC-BY-NC 4.0. This repository only ships a derived Core ML export for on-device use; the same license restrictions apply.

Intended use

  • macOS / iOS on-device translation via MLModel (or coremltools in Python for validation).
  • Language direction is controlled in your app: tokenizer src_lang, forced target BOS (e.g. eng_Latn), and your beam/greedy loop around Decoder_256_step.
  • Compare accuracy and latency against the float32 sibling on your devices; palettization can change numerical behavior.

Limitations

  • Fixed max sequence length 256 at export time; longer inputs require truncation or a different export.
  • Not a drop-in Hugging Face transformers checkpoint; this is a split Core ML deployment (encoder + decoder packages).

Maintainer

aoiandroid