Instructions to use Helsinki-NLP/opus-mt-tr-ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-tr-ar 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-tr-ar")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-tr-ar") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-tr-ar", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
5b41dfb
-
Adding generation config file(s)
8cd1cc4
-
Add TF weights
Joao Gante94ee485
-
Update README.md
9883a63 -
Update README.md
9d63455 -
Update metadata.json
5c3c0e7
-
Update README.md
de453d6 -
Update README.md
4a1f8a6 -
Update metadata.json
dfc9d7d -
Update README.md
216709e -
Update config.json
b3ca774 -
Update metadata.json
d0b1ec5 -
Update pytorch_model.bin
14d5cc9 -
Update source.spm
20cf737 -
Update target.spm
4deeffb -
Update tokenizer_config.json
d6f45a4 -
Update vocab.json
7d01a20 -
initial commit
8be88b7