Translation
Transformers
PyTorch
TensorFlow
Safetensors
English
Somali
cus
marian
text2text-generation
Instructions to use Helsinki-NLP/opus-mt-en-cus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-en-cus 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-cus")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-cus") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-cus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Adding `safetensors` variant of this model (#2)
- Adding `safetensors` variant of this model (018ea1a6d1dcb001a8415841a679d1c2f57a1312) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>5d95c73
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
f883dd6
-
Adding generation config file(s)
b9690a7
-
Add TF weights
Joao Gantefad2a48
-
Changed num_beams to 4
495278a
-
Update README.md
95f17c3 -
Update README.md
6df7703 -
Update metadata.json
720993f
-
Update README.md
851180e -
Update config.json
9c60527 -
Update metadata.json
98f36fa -
Update tokenizer_config.json
b653bc4 -
Update vocab.json
ca6d797 -
Update README.md
96dceea -
Update metadata.json
7064a3b -
Update README.md
4f6ed46 -
Update config.json
b986461 -
Update metadata.json
bb53a31 -
Update pytorch_model.bin
5cb47b6 -
Update source.spm
b6e89e6 -
Update target.spm
cfd5e58 -
Update tokenizer_config.json
71d41ee -
Update vocab.json
2ffd340 -
initial commit
fbda4bc