Instructions to use Helsinki-NLP/opus-mt-cpp-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-cpp-en 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-cpp-en")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-cpp-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-cpp-en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
92939b8
-
Adding generation config file(s)
9c19b14
-
Add TF weights
Joao Ganteabb1886
-
Changed num_beams to 4
523c5f7
-
Update README.md
662d0a0 -
Update README.md
bb037ce -
Update metadata.json
5072ece
-
Update README.md
2d182fe -
Update config.json
0a40ca1 -
Update metadata.json
aacc427 -
Update tokenizer_config.json
f5ccda4 -
Update vocab.json
dc5f32f -
Update README.md
d1fc93e -
Update metadata.json
596f47b -
Update README.md
b94bce1 -
Update config.json
aabe87a -
Update metadata.json
5d8d4be -
Update pytorch_model.bin
37cafbc -
Update source.spm
4f66697 -
Update target.spm
c300bc6 -
Update tokenizer_config.json
c7791c3 -
Update vocab.json
7586eca -
initial commit
31b1a94