Instructions to use Helsinki-NLP/opus-mt-de-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-de-it 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-de-it")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-de-it") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-de-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
9038fd0
-
Adding generation config file(s)
ba438de
-
Add TF weights
Joao Gante7ef555a
-
metadata: add license
cd2319a
-
Changed num_beams to 4
57d967b
-
Update README.md
e530299
-
Update README.md
f336173 -
Update config.json
4a36880 -
Update tokenizer_config.json
83fed1e -
Update vocab.json
11c8e95
-
Update README.md
a486773 -
Update config.json
317d2a1 -
Update tokenizer_config.json
93352bf -
Update vocab.json
38273e4 -
Update README.md
90ad74e
-
Update README.md
b3ecb50 -
Update README.md
8bdb59b
-
Update README.md
3a1532f
-
Update README.md
fc7d887
-
Update config.json
8884dc5 -
Update config.json
5a08001
-
Update config.json
9289c8a -
Update config.json
5faa298
-
Update source.spm
fbe0c58 -
Update target.spm
7ebd6dd -
Update tokenizer_config.json
40c12dc -
Update vocab.json
224f587 -
Update config.json
2eba0b0 -
Update pytorch_model.bin
1f16b05 -
initial commit
3fb145e