pszemraj/long-t5-tglobal-base-16384-book-summary
summarization model by pszemraj
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Summarize long text and get a SparkNotes-esque summary of arbitrary topics! A summary of the infamous navy seals copypasta: Contents A fine-tuned version of google/long-t5-tglobal-base on the kmfoda/booksum dataset: Read the paper by Guo et al. here: LongT5: Efficient Text-To-Text Transformer for Long Sequences Install/update transformers pip install -U transformers Summarize text with pipeline: Pass other parameters related to beam search textgen when calling summarizer to get even higher quality results. kmfoda/booksum dataset on HuggingFace - read the original paper here. Summaries longer than 1024 LongT5 tokens were filtered out to prevent the model from learning to generate "partial" summaries. See summarize.py in the code for my hf space Document Summarization :) You can also use the same code to split a document into batches of 4096, etc., and run over those with the model. This is useful in situations where CUDA memory is limited. See train with a script…
Read the full model card ↗ · Preview checked 2026-10-08T06:43:16.696Z
Inside the original model card — Document outline
- long-t5-tglobal-base-16384 + BookSum
- Cheeky Proof-of-Concept
- Model description
- How-To in Python
- Intended uses & limitations
- Training and evaluation data
- FAQ
- How to run inference over a very long (30k+ tokens) document in batches?
- How to fine-tune further?
- Are there simpler ways to run this?
- Training procedure
- Updates:
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
pszemraj/long-t5-tglobal-base-16384-book-summary is a summarization model repository published by pszemraj on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- summarization
- Library
- transformers
- Recent downloads (30 days)
- 405
- Cumulative likes
- 136
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 247,587,456
- Architecture
- LongT5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2022-06-27T16:37:26.000Z
- Last modified
- 2025-12-29T03:38:50.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-08T06:42:16.381Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
pszemraj/long-t5-tglobal-base-sci-simplify