Instructions to use Helsinki-NLP/opus-mt-ms-ms with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ms-ms 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-ms")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ms-ms") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ms-ms", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
ed82561
-
Adding generation config file(s)
0a997c8
-
Add TF weights
Joao Gantecef85d5
-
Update README.md
5319301 -
Update README.md
80efdbc -
Update metadata.json
5bf524c
-
Update README.md
55f691d -
Update config.json
86dc53c -
Update metadata.json
3b0da74 -
Update tokenizer_config.json
762a5a1 -
Update vocab.json
a21e436 -
Update README.md
6b9a5ba -
Update metadata.json
392db84 -
Update README.md
6ac71b8 -
Update config.json
ad28487 -
Update metadata.json
83153a5 -
Update pytorch_model.bin
91b877a -
Update source.spm
d18c8fe -
Update target.spm
7afc7ea -
Update tokenizer_config.json
3a41b7b -
Update vocab.json
50418dc -
initial commit
6cc31e8