translation_en_ru

Эта модель дообучена на Helsinki-NLP/opus-mt-en-ru с помощью датасета tico19, который содержит терминологию связанную с COVID-19. Модель может использоваться для перевода медицинских текстов

Результаты на тестовых данных:

  • Loss: 1.1217
  • Bleu: 30.84

Запуск модели

from transformers import pipeline

model_checkpoint = "glazzova/ml_translation_model1"
translator = pipeline("translation", model=model_checkpoint)
translator("i have a little cold and a cough")

# у меня есть простуда и кашель

Гиперпараметры

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
50
Safetensors
Model size
76.2M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for glazzova/translation_en_ru

Finetuned
(13)
this model

Dataset used to train glazzova/translation_en_ru