Instructions to use Helsinki-NLP/opus-mt-en-mg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-en-mg 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-mg")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-mg") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-mg", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
19162a2
-
Adding generation config file(s)
4cf467a
-
Add TF weights
Joao Gante04ada2c
-
metadata: add license
83bbfea
-
Changed num_beams to 4
51d7c17
-
Update README.md
2f50236
-
Update README.md
7daf2bb -
Update config.json
ecf4481 -
Update tokenizer_config.json
34c33d6 -
Update vocab.json
f0fa529
-
Update README.md
bac9033 -
Update config.json
1d9448c -
Update tokenizer_config.json
ad89d31 -
Update vocab.json
07a4e22 -
Update README.md
a937809
-
Update README.md
8f44f07 -
Update README.md
ef21d20
-
Update README.md
0e25e74
-
Update README.md
35ece81
-
Update config.json
8c1f256 -
Update config.json
db170c9
-
Update config.json
df7e456 -
Update config.json
0c4e4a0
-
Update source.spm
10871b7 -
Update target.spm
73b090b -
Update tokenizer_config.json
c3a3f1d -
Update vocab.json
372733e -
Update config.json
363d87d -
Update pytorch_model.bin
53355ab -
initial commit
280eb84