How to use Babelscape/mrebel-base 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="Babelscape/mrebel-base")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Babelscape/mrebel-base") model = AutoModelForSeq2SeqLM.from_pretrained("Babelscape/mrebel-base", device_map="auto")
https://huggingface.co/Babelscape/mrebel-base/resolve/main/vocab.json
hf download hf://Babelscape/mrebel-base/vocab.json
curl -L -o vocab.json https://huggingface.co/Babelscape/mrebel-base/resolve/main/vocab.json
