translate-windy-hplt-vi-en — vi to en

Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-windy-hplt-vi-en

Bilingual machine translation in CTranslate2 INT8 for fast CPU inference. Fine-tuned by Windstorm Labs from HPLT/translate-vi-en-v2.0-hplt_opus.

Attribution

Derived from HPLT/translate-vi-en-v2.0-hplt_opus, from the HPLT project, licensed under CC-BY-4.0. Modified by Windstorm Labs. Attribution is retained as the licence requires.

What we did

Converted from the upstream Marian release, LoRA fine-tuned on parallel data for this language pair, merged into the base weights, then quantized to INT8.

Rank / alpha	8 / 16
Learning rate / steps	2.5e-06 / 50
Target modules	q_proj, v_proj
Seed	42
Training data	opus100_vi-en, 2,000 sentence pairs
Tensors modified	36

Provenance

base model.bin  sha256  676bff86db01ed15a4e728d86d2f7843a2a3da50f4b3778a7678a6ad1f3436e0
this model.bin  sha256  6ca35e50f4adec6e54344f68c54841e47263b8c2e7793d121b8175e0896c188e

Verified after INT8 quantization, on the published artifact.

Evaluation

FLORES-200 devtest, 200 sentences, beam 4, CTranslate2 INT8 on CPU.

	spBLEU	chrF
this model	37.55	60.39

Notes

• Single language pair: vi to en.
• FLORES-200 is news and encyclopedic prose.
• No human evaluation was performed.