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
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
e1ed571
-
Adding generation config file(s)
96f67c2
-
Add TF weights
Joao Gante07f23c0
-
Update README.md
db108c7 -
Update README.md
d7f074b -
Update metadata.json
eee62c2
-
Update README.md
ddf2d4a -
Update config.json
a3b5134 -
Update metadata.json
91d2d7b -
Update tokenizer_config.json
2b7534e -
Update vocab.json
e8084b2 -
Update README.md
456a436 -
Update metadata.json
52e0c2a -
Update README.md
cbcb960 -
Update config.json
2d923d9 -
Update metadata.json
765928c -
Update pytorch_model.bin
206d1c9 -
Update source.spm
b90b1ad -
Update target.spm
333d8a7 -
Update tokenizer_config.json
f349cc7 -
Update vocab.json
809223a -
initial commit
1aebed4