Instructions to use Helsinki-NLP/opus-mt-ms-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ms-it 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-it")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ms-it") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ms-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
c7ba94f
-
Adding generation config file(s)
fea05ed
-
Add TF weights
Joao Gante6b9c98b
-
Update README.md
0e002c3 -
Update README.md
f648dcb -
Update metadata.json
06a4377
-
Update README.md
66dd21b -
Update config.json
8f5e46f -
Update metadata.json
a10cb1a -
Update tokenizer_config.json
508f0c8 -
Update vocab.json
1817973 -
Update README.md
6de22c8 -
Update metadata.json
7875745 -
Update README.md
0982265 -
Update config.json
4e22010 -
Update metadata.json
0797314 -
Update pytorch_model.bin
840fd89 -
Update source.spm
a4ea8dc -
Update target.spm
3eb559a -
Update tokenizer_config.json
99d5a30 -
Update vocab.json
50c6abe -
initial commit
56bd39c