How to use FkSg16KN/marian-finetuned-kde4-en-to-fr 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="FkSg16KN/marian-finetuned-kde4-en-to-fr")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("FkSg16KN/marian-finetuned-kde4-en-to-fr") model = AutoModelForSeq2SeqLM.from_pretrained("FkSg16KN/marian-finetuned-kde4-en-to-fr", device_map="auto")
https://huggingface.co/FkSg16KN/marian-finetuned-kde4-en-to-fr/resolve/36f95eb7b52595df8422c5d1c9db75c0f811fcda/source.spm
hf download hf://FkSg16KN/marian-finetuned-kde4-en-to-fr@36f95eb7b52595df8422c5d1c9db75c0f811fcda/source.spm
curl -L -o source.spm https://huggingface.co/FkSg16KN/marian-finetuned-kde4-en-to-fr/resolve/36f95eb7b52595df8422c5d1c9db75c0f811fcda/source.spm
