Instructions to use Helsinki-NLP/opus-mt-de-mt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-de-mt 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-de-mt")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-de-mt") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-de-mt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
2555008
-
Adding generation config file(s)
c831650
-
Add TF weights
Joao Gante8a19643
-
metadata: add license
0d71c2c
-
Changed num_beams to 4
566fd34
-
Update README.md
4d41fbb
-
Update README.md
4b34e4c -
Update config.json
701eef4 -
Update tokenizer_config.json
733fd67 -
Update vocab.json
392bd0f
-
Update README.md
e4bdfbb -
Update config.json
3932d52 -
Update tokenizer_config.json
2d34620 -
Update vocab.json
0dcdecf -
Update README.md
c8650ce
-
Update README.md
316ae9a -
Update README.md
edf7ed7
-
Update README.md
9485890
-
Update README.md
f1ebb54
-
Update config.json
46f3d52 -
Update config.json
183f2ff
-
Update config.json
2ff99ee -
Update config.json
f43d9aa
-
Update tokenizer_config.json
fd85211 -
Update vocab.json
1cb8ece -
Update source.spm
d4a989e -
Update target.spm
75f1007 -
Update config.json
4619f65 -
Update pytorch_model.bin
45ac8b6 -
initial commit
52361eb