Instructions to use Helsinki-NLP/opus-mt-it-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-it-en 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-it-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-it-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-it-en") - Inference
- Notebooks
- Google Colab
- Kaggle
Model Card
#1
by Ezi - opened
This part
CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes."
sounds too harsh to me. It's a translation model - what is disturbing about this model? This could scare users away unnecessarily. If we add something like this to the model card we should also add examples that showcase this behavior.
Also cc @tiedeman