Instructions to use Helsinki-NLP/opus-mt-ca-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-ca-pt 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-ca-pt")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ca-pt") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ca-pt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
5142c1f
-
Adding generation config file(s)
35e50f0
-
Add TF weights
Joao Ganteb0f785c
-
Changed num_beams to 4
272ac90
-
Update README.md
eb3871c -
Update README.md
c28a95e -
Update metadata.json
a214210
-
Update README.md
95dc05c -
Update config.json
e81955c -
Update metadata.json
bbca1db -
Update tokenizer_config.json
ad7cc22 -
Update vocab.json
9f8a6a7 -
Update README.md
161f38d -
Update metadata.json
ef9be1a -
Update README.md
fab082f -
Update config.json
b9632ee -
Update metadata.json
ae32891 -
Update pytorch_model.bin
6512ae4 -
Update source.spm
1653674 -
Update target.spm
5c75605 -
Update tokenizer_config.json
9396a14 -
Update vocab.json
013cba9 -
initial commit
f77694d