How to use Helsinki-NLP/opus-mt-gem-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-gem-en")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-gem-en") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-gem-en", device_map="auto")
https://huggingface.co/Helsinki-NLP/opus-mt-gem-en/resolve/refs%2Fpr%2F1/tokenizer_config.json
hf download hf://Helsinki-NLP/opus-mt-gem-en@refs/pr/1/tokenizer_config.json
curl -L -o tokenizer_config.json https://huggingface.co/Helsinki-NLP/opus-mt-gem-en/resolve/refs%2Fpr%2F1/tokenizer_config.json
