How to use from the
Use from the
Transformers.js library
// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('translation', 'OptimaMT/en-ar');

OptimaMT en β†’ ar (English to Arabic)

Drop-in copy of Xenova/opus-mt-en-ar at revision 034a684356c1 with a lighter merged decoder: ONNX Runtime's fast mode (disable_quant_qdq = 1, 2.3–2.5Γ— faster) at half the memory. Same weights, same tokens. Part of OptimaMT: all 51 pairs, named OptimaMT/<src>-<tgt>.

Used in production:

  • OpenCircle, a desktop screen translator for Windows and Linux, ships these models since v0.1.4.
Memory after load Linux Windows Identical tokens
disable_quant_qdq = 1 527 β†’ 282 MiB (-46 %) 504 β†’ 256 MiB (-49 %) yes
ONNX Runtime defaults 282 β†’ 220 MiB (-22 %) 198 β†’ 166 MiB (-16 %) yes

FLORES-200 devtest (1,012 sentences): the same translations as the original, BLEU 22.03, chrF 54.14 (greedy).

ONNX Runtime 1.31.1, CPU, 4 threads (Linux; Windows in a VM). Interactive results: OptimaMT/results Β· method: REPORT.md.

Use

import { pipeline } from "@huggingface/transformers";

const translator = await pipeline("translation", "OptimaMT/en-ar", {
  dtype: "q8",
  session_options: { extra: { session: { disable_quant_qdq: "1" } } },
});
const [out] = await translator(">>ara<< The lighthouse stands on the coast.");
console.log(out.translation_text);

Python (translate.py: onnxruntime, sentencepiece, numpy):

python translate.py OptimaMT/en-ar "The lighthouse stands on the coast." --lang ">>ara<<"

Start every input with >>ara<< (the target variant). Use transformers.js 3.x: 4.3.2 splits this token, with the original export too.

Files

Only onnx/decoder_model_merged_quantized.onnx is rebuilt; every other file is the original, byte for byte. Vocabulary: 62,802 tokens.

Licence and credits

  • Weights: OPUS-MT by the University of Helsinki, CC BY 4.0.
  • ONNX export: Xenova/opus-mt-en-ar at revision 034a684356c1.
  • Modified: the decoder's output projection was moved out of its two branches (graph change only). CC BY 4.0.
Downloads last month
48
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for OptimaMT/en-ar

Quantized
(1)
this model

Space using OptimaMT/en-ar 1

Collection including OptimaMT/en-ar