Helsinki-NLP/opus-mt_tiny_eng-rus

OPUS-MT-tiny-rus-eng

Distilled model from a Tatoeba-MT Teacher: OPUS-MT-models/en-ru/opus-2020-02-11, which has been trained on the Tatoeba dataset.

We used the OpusDistillery to train new a new student with the tiny architecture, with a regular transformer decoder. For training data, we used Tatoeba. The configuration file fed into OpusDistillery can be found here.

How to run

from transformers import MarianMTModel, MarianTokenizer
model_name = "Helsinki-NLP/opus-mt_tiny_eng-rus"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
tok = tokenizer("Hello, how are you?", return_tensors="pt").input_ids
output = model.generate(tok)[0]
tokenizer.decode(output, skip_special_tokens=True)

Benchmarks

Teacher

testset	BLEU	chr-F	COMET
Flores+	25.8	53.9	0.8459
Bouquet	31.8	55.3	0.8685

Student

testset	BLEU	chr-F	COMET
Flores+	24.4	52.0	0.8122
Bouquet	28.0	53.0	0.8243