Instructions to use Helsinki-NLP/opus-mt-tr-lt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-tr-lt 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-lt")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-tr-lt") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-tr-lt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
8dc0e79
-
Adding generation config file(s)
88f2b47
-
Update README.md
4775ec9 -
Update README.md
98153f9 -
Update metadata.json
23ea1eb
-
Update README.md
613066f -
Update README.md
7b333e9 -
Update metadata.json
2757620 -
Update vocab.json
bc60433 -
Update README.md
066fa5f -
Update config.json
9078343 -
Update metadata.json
2f1e625 -
Update pytorch_model.bin
1f37bf1 -
Update source.spm
6cbc501 -
Update target.spm
1cbfc86 -
Update tokenizer_config.json
e4d496f -
initial commit
b5bbeea