Instructions to use Helsinki-NLP/opus-mt-ru-uk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ru-uk with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-ru-uk")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ru-uk") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ru-uk", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Helsinki-NLP/opus-mt-ru-uk: direct link, hf CLI and curl.
- Browser
- Download file 44 Bytes
-
https://huggingface.co/Helsinki-NLP/opus-mt-ru-uk/resolve/eee62c269db59d835e435a92c10e4fedef871127/tokenizer_config.json
- Command line
-
hf download hf://Helsinki-NLP/opus-mt-ru-uk@eee62c269db59d835e435a92c10e4fedef871127/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Helsinki-NLP/opus-mt-ru-uk/resolve/eee62c269db59d835e435a92c10e4fedef871127/tokenizer_config.json
44 Bytes
| {"target_lang": "ukr", "source_lang": "rus"} |