Instructions to use Helsinki-NLP/opus-mt-ms-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ms-de 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-ms-de")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ms-de") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ms-de", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
57d4d41
-
Adding generation config file(s)
733f300
-
Add TF weights
Joao Gante46a6953
-
Update README.md
29f3de8 -
Update README.md
9277d9a -
Update metadata.json
82020b8
-
Update README.md
f3cbfb6 -
Update config.json
2c0f3cf -
Update metadata.json
d9b7122 -
Update tokenizer_config.json
010d539 -
Update vocab.json
6035c79 -
Update README.md
f659329 -
Update metadata.json
cbcd167 -
Update README.md
1303f0f -
Update config.json
202315f -
Update metadata.json
c871752 -
Update pytorch_model.bin
a023e74 -
Update source.spm
3bc4b39 -
Update target.spm
da2f64d -
Update tokenizer_config.json
6f51632 -
Update vocab.json
0685ce8 -
initial commit
fd2bfa6