bigbird pegasus on the booksum dataset

this is the "latest" version of the model that has been trained the longest, currently at 70k steps

• GOAL: A summarization model that 1) summarizes the source content accurately 2) more important IMO produces summaries that are easy to read and understand (* cough * unlike arXiv * cough *)
  • This model attempts to help with that by using the booksum dataset to provide explanatory summarization
  • Explanatory Summary - A summary that both consolidates information and also explains why said consolidated information is important.
• This model was trained for seven epochs total (approx 70,000 steps) and is closer to finished.
  • Will continue to improve (slowly, now that it has been trained for a long time) based on any result findings/feedback.
• starting checkpoint was google/bigbird-pegasus-large-bigpatent

example usage

An extended example, including a demo of batch summarization, is here.

• create the summarizer object:

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from transformers import pipeline

model = AutoModelForSeq2SeqLM.from_pretrained(
    "pszemraj/bigbird-pegasus-large-K-booksum",
    low_cpu_mem_usage=True,
)

tokenizer = AutoTokenizer.from_pretrained(
    "pszemraj/bigbird-pegasus-large-K-booksum",
)


summarizer = pipeline(
    "summarization",
    model=model,
    tokenizer=tokenizer,
)          

• define text to be summarized, and pass it through the pipeline. Boom done.

wall_of_text = "your text to be summarized goes here."

result = summarizer(
    wall_of_text,
    min_length=16,
    max_length=256,
    no_repeat_ngram_size=3,
    clean_up_tokenization_spaces=True,
)

print(result[0]["summary_text"])

Alternate Checkpoint

• if experiencing runtime/memory issues, try this earlier checkpoint at 40,000 steps which is almost as good at the explanatory summarization task but runs faster.
• see similar summarization models fine-tuned on booksum but using different architectures: long-t5 base and LED-Large