Downloads · 30 days
5
10% of all-time downloads
WindyTranslate/translate-windy-hplt-cy-en
translate-windy-hplt-cy-en is a translation model from WindyTranslate. Use it when you need text moved from one language to another. It is set up for ctranslate2. The card lists the license as cc-by-4.0.
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-windy-hplt-cy-en
Downloads · 30 days
5
10% of all-time downloads
All-time downloads
51
Public
Repo size
80.4 MB
Likes
0
Public
Click a slice to open those files.
.bin79 MB · 94%
From the Hugging Face model README
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-windy-hplt-cy-en
CTranslate2 INT8 bilingual translation model, derived from
HPLT/translate-cy-en-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.
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.
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_cy-en, 2000 sentence pairs |
| Tensors modified | 36 |
| Max absolute weight delta | 3.754e-05 |
base model.bin sha256 f529fbc845abf41fa87c0d9ad30b3d3e98f3c3aaa57673c59a70418773cfeace
this model.bin sha256 5305d43f07351d0f00bcd9fe708aebc322d2566f12308ea1d7ea9156b9e7a523
Verified on the quantized artifact you download, not merely internal weights.
FLORES-200 devtest, 200 sentences, beam 4, CTranslate2 INT8 on CPU.
Metrics: spBLEU (flores200 tokenizer) + chrF (word_order=0).
| spBLEU | chrF | |
|---|---|---|
| this model | 48.79 | 68.92 |
| upstream, pre-fog | 47.53 | — |