How to use taskload/reduce-bart with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("taskload/reduce-bart") model = AutoModelForSeq2SeqLM.from_pretrained("taskload/reduce-bart", device_map="auto")
https://huggingface.co/taskload/reduce-bart/resolve/refs%2Fpr%2F1/vocab.json
hf download hf://taskload/reduce-bart@refs/pr/1/vocab.json
curl -L -o vocab.json https://huggingface.co/taskload/reduce-bart/resolve/refs%2Fpr%2F1/vocab.json
