Instructions to use Helsinki-NLP/opus-mt-en-bi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-en-bi 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-en-bi")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-bi") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-bi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
5d7c8d4
-
Adding generation config file(s)
b933eb3
-
Add TF weights
Joao Gante878ea39
-
metadata: add license
b3e9ed5
-
Changed num_beams to 4
5afa2f3
-
Update README.md
300e07d
-
Update README.md
14e8d21 -
Update config.json
946f945 -
Update tokenizer_config.json
2c8ca8c -
Update vocab.json
5ab0c2a
-
Update README.md
250e78e -
Update config.json
8130824 -
Update tokenizer_config.json
bbae5cb -
Update vocab.json
50fc56b -
Update README.md
52bfc96
-
Update README.md
e131cc5 -
Update README.md
c40e8de
-
Update README.md
fdeada1
-
Update README.md
93574c4
-
Update config.json
a5a9eb7 -
Update config.json
744cac3
-
Update config.json
0fab306 -
Update config.json
ae4bb4e
-
Update source.spm
0b323ee -
Update target.spm
5a63950 -
Update tokenizer_config.json
331f92f -
Update vocab.json
b9863fa -
Update config.json
919ed6d -
Update pytorch_model.bin
054b47e -
initial commit
96c466b