Modelpublic

WindyWord/translate-windy-hplt-en-ms

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face

0likes8downloads

Model Card

translate-windy-hplt-en-ms — en to ms

CTranslate2 INT8 bilingual translation model, derived from `HPLT/translate-en-ms-v2.0-hplt_opus` (the HPLT project, CC-BY-4.0).

CC-BY-4.0 permits commercial use and modification and requires attribution; this notice provides it. Windstorm Labs did not train the base model.

Recovery note

HPLT publishes native Marian (.npz + .spm + .vocab) and marks its repos inference: false. An earlier conversion of this model to transformers format corrupted the weights, producing untranslatable output, and the model was written off. It was recovered on 2026-07-26 by converting the original .npz with the official Marian converter. The model was always fine; the conversion was not.

What was changed

A deliberately minimal LoRA fine-tune ("windy hallmark") merged into the base weights.


Rank / alpha	8 / 16
Learning rate / steps	2.5e-06 / 50
Target modules	`q_proj`, `v_proj`
Seed	42 (reproducible)
Training data	opus100_en-ms (clinic cache), 2000 sentence pairs
Tensors modified	36
Max absolute weight delta	3.993e-05

Provenance

base   model.bin sha256  7291b87573345a69c6168e447ea0dba3bba0bfeeb537ce506403120fd3abfb9e
this   model.bin sha256  12a0a88c880dfd7cf6b3c685740806106931678c687f53b0e4456305debe33bb

Verified on the quantized artifact you download, not merely internal weights.

Evaluation

FLORES-200 devtest, 200 sentences, beam 4, CTranslate2 INT8 on CPU. Metrics: spBLEU (flores200 tokenizer) + chrF (word_order=0).

	spBLEU	chrF
this model	26.38	55.5
upstream, pre-fog	25.39	—

Limitations

—One language pair only (en to ms).
—FLORES-200 is news and encyclopedic prose; it says little about conversational register.
—No human evaluation was performed.