Instructions to use Helsinki-NLP/opus-mt-en-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-en-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-en-zh")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-zh") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-zh", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
This model could not covert to BetterTransformer model
#9
by DDDSSS - opened
print(model)
#%%
from optimum.bettertransformer import BetterTransformer
from transformers import AutoModel
mode_name = 'Helsinki-NLP/opus-mt-en-zh'
model = AutoModel.from_pretrained(mode_name)
model = model.to(0)
model_bt = BetterTransformer.transform(model)
ValueError: Activation function swish not supported for BetterTransformer integration.