How to use Rostlab/ProstT5 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="Rostlab/ProstT5")
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Rostlab/ProstT5") model = AutoModelForSeq2SeqLM.from_pretrained("Rostlab/ProstT5", device_map="auto")
https://huggingface.co/Rostlab/ProstT5/resolve/refs%2Fpr%2F1/prostt5_sketch2.png
hf download hf://Rostlab/ProstT5@refs/pr/1/prostt5_sketch2.png
curl -L -o prostt5_sketch2.png https://huggingface.co/Rostlab/ProstT5/resolve/refs%2Fpr%2F1/prostt5_sketch2.png
