Instructions to use Helsinki-NLP/opus-mt-de-ZH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-de-ZH 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-ZH")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-de-ZH") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-de-ZH") - Notebooks
- Google Colab
- Kaggle
Cannot make the model produce anything else than the pad token
#2
by marcelklehr - opened
Hi
For some reason this model (other models from Helsinki-NLP are fine) will not produce any other tokens than the pad token, even when I'm adding the necessary language code token for the input. What am I missing? Is this model broken?