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