How to use orzhan/t5-long-extract with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="orzhan/t5-long-extract")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("orzhan/t5-long-extract") model = AutoModel.from_pretrained("orzhan/t5-long-extract", device_map="auto")
https://huggingface.co/orzhan/t5-long-extract/resolve/main/tokenizer.json
hf download hf://orzhan/t5-long-extract/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/orzhan/t5-long-extract/resolve/main/tokenizer.json
