Edit model card
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("ArvinZhuang/BiTAG-t5-large")
tokenizer = AutoTokenizer.from_pretrained("ArvinZhuang/BiTAG-t5-large")

text = "abstract: [your abstract]"  # use 'title:' as the prefix for title_to_abs task.
input_ids = tokenizer.encode(text, return_tensors='pt')

outputs = model.generate(
    input_ids,
    do_sample=True,
    max_length=500,
    top_p=0.9,
    top_k=20,
    temperature=1,
    num_return_sequences=10,
)

print("Output:\n" + 100 * '-')
for i, output in enumerate(outputs):
    print("{}: {}".format(i+1, tokenizer.decode(output, skip_special_tokens=True)))

GitHub: https://github.com/ArvinZhuang/BiTAG

Downloads last month
16
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.