t5 small booksum

Providercnicu
Categorysummarization
Licensemit
Downloads18.6K
Stars0

Overview

The t5-small-booksum model is a specialized encoder-decoder transformer fine-tuned specifically for long-form narrative summarization. Unlike general-purpose T5 models, this variant is optimized for the BookSum dataset, making it highly effective for condensing chapters or entire plot arcs into concise summaries while maintaining narrative flow. For developers, its 'small' architecture ensures low latency and minimal VRAM overhead, allowing for efficient deployment on CPU-only environments or edge devices. It serves as a practical tool for building reading assistants, content archival systems, or automated plot indexing tools where high throughput is prioritized over the deep reasoning capabilities of larger LLMs.

Highlights

  • Optimized for long-form narrative and book summarization
  • Low latency deployment on CPU and edge hardware
  • Lightweight T5 architecture reduces operational infrastructure costs
  • MIT licensed for flexible commercial and private integration

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("cnicu/t5-small-booksum")
tokenizer = AutoTokenizer.from_pretrained("cnicu/t5-small-booksum")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download cnicu/t5-small-booksum

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download cnicu/t5-small-booksum config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('cnicu/t5-small-booksum')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/cnicu/t5-small-booksum

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/cnicu/t5-small-booksum

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('cnicu/t5-small-booksum')
tokenizer = AutoTokenizer.from_pretrained('cnicu/t5-small-booksum')

Full Documentation

来源: HuggingFace

---
license: mit
tags:

  • summarization

  • summary

datasets:
  • kmfoda/booksum


---

View official source
Join our Telegram