translate-ilo-en

Machine translation model, ilo to en, published by Windstorm Labs.

Attribution

Derived from Helsinki-NLP/opus-mt-ilo-en, licensed apache-2.0. Windstorm Labs did not train the original model. This notice provides the attribution the licence requires.

What was changed

The weights in this repository have been modified from the original. A full fine-tune on OPUS-100 parallel corpus data.

Method deep-finetune
Tensors modified 253 of 254
Max absolute weight delta 1.871e-03
Verified tensor-by-tensor against the upstream original, 2026-07-26

The comparison is tensor-level rather than file-level: safetensors and PyTorch .bin containers hash differently even when the tensors inside are identical, so a file-hash mismatch would prove nothing.

Contents

A single transformers build in safetensors format, loadable directly:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tok = AutoTokenizer.from_pretrained("WindyTranslate/translate-ilo-en")
model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-ilo-en")

batch = tok(["<your text here>"], return_tensors="pt", padding=True)
print(tok.batch_decode(model.generate(**batch), skip_special_tokens=True))

Other builds of this pair, including CTranslate2 INT8, are not included in this repository.

Limitations

  • A single language direction: ilo to en.
  • No quality benchmark has been run on this pair. The weights are verified to differ from the original; that is a statement about provenance, not about translation quality.
  • Quality is not monotonic with model size or with the amount of fine-tuning applied.
Downloads last month
-
Safetensors
Model size
55.5M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for WindyTranslate/translate-ilo-en

Finetuned
(1)
this model