Instructions to use Helsinki-NLP/opus-mt-eo-sh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-eo-sh 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-eo-sh")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-eo-sh") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-eo-sh", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
451d09c
-
Adding generation config file(s)
8bd2e7c
-
Add TF weights
Joao Ganteb007250
-
Changed num_beams to 4
64f5856
-
Update README.md
59ab4ad -
Update README.md
46bfae5 -
Update metadata.json
5235ead
-
Update README.md
e860c9e -
Update config.json
1d9c386 -
Update metadata.json
b011673 -
Update tokenizer_config.json
f3df93b -
Update vocab.json
a9e08eb -
Update README.md
b197067 -
Update metadata.json
9cf384b -
Update README.md
a9f912e -
Update config.json
30eac2d -
Update metadata.json
63600d0 -
Update pytorch_model.bin
5176fd9 -
Update source.spm
c01a676 -
Update target.spm
ca056be -
Update tokenizer_config.json
b285570 -
Update vocab.json
f8dc937 -
initial commit
52316e9