Gemma 2 9B Document Summariser

Published by @compressor_ai · Community adapter

Abstractive summarisation tuned on news articles, research papers, and legal documents. Produces structured summaries with TL;DR, key points, and action items.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
base = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it")
model = PeftModel.from_pretrained(base, "modelforgelab/gemma2-9b-summarizer-lora")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• transformers>=4.42