Long T5 Tglobal Base Synthsumm Direct

🚀 long-t5-tglobal-base-synthsumm_direct

A fine - tuned model for summarization, trained on a synthetic dataset to handle long - context text.

This model is fine - tuned on a synthetic dataset that includes curated long - context text and GPT - 3.5 - turbo - 1106 summaries across multiple domains, along with "random" long - context examples from pretraining datasets.

• Note: this model has not been fine - tuned on any other summarization datasets, just the synthsumm data.

Try it: gradio demo | free HF inference api via requests| .md with example outputs (gauntlet)

🚀 Quick Start

📦 Installation

It's recommended to use this model with beam search decoding. If interested, you can also use the textsum util repo to have most of this abstracted out for you. Install it using the following command:

pip install -U textsum

💻 Usage Examples

Basic Usage

from textsum.summarize import Summarizer

model_name = "pszemraj/long-t5-tglobal-base-synthsumm_direct"
summarizer = Summarizer(model_name) # GPU auto-detected
text = "put the text you don't want to read here"
summary = summarizer.summarize_string(text)
print(summary)

📚 Documentation

Model Details

This model is a fine - tuned version of [google/long - t5 - tglobal - base](https://huggingface.co/google/long - t5 - tglobal - base) on the None dataset. It achieves the following results on the evaluation set:

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Framework versions

📄 License

This project is licensed under the Apache - 2.0 license.