# led-large-book-summary by Peter Szemraj: Open-Weight Model
Source: https://savrn.com/models/led-large-book-summary
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve led-large-book-summary (460M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
| --- | --- | --- | --- | --- | --- |
| 16-bit | 0.9 GB | 1.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 8-bit | 0.5 GB | 0.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 4-bit | 0.2 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026.

[led-large-book-summary on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/led-large-book-summary/gpus)

## Model Card

By Peter Szemraj, published under apache-2.0, revision 600de3bbcdb1.

This model is a fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the BookSum dataset (kmfoda/booksum). It aims to generalize well and be useful in summarizing lengthy text for both academic and everyday purposes.

- Handles up to 16,384 tokens input
- See the Colab demo linked above or try the [demo on Spaces](https://huggingface.co/spaces/pszemraj/summarize-long-text)

Note: Due to inference API timeout constraints, outputs may be truncated before the fully summary is returned (try python or the demo)

### Basic Usage

To improve summary quality, use encoder_no_repeat_ngram_size=3 when calling the pipeline object. This setting encourages the model to utilize new vocabulary and construct an abstractive summary.

Load the model into a pipeline object:

```
import torch
from transformers import pipeline

hf_name = 'pszemraj/led-large-book-summary'

summarizer = pipeline(
    "summarization",
    hf_name,
    device=0 if torch.cuda.is_available() else -1,
)
```

Feed the text into the pipeline object:

```
wall_of_text = "your words here"

result = summarizer(
    wall_of_text,
    min_length=16,
    max_length=256,
    no_repeat_ngram_size=3,
    encoder_no_repeat_ngram_size=3,
    repetition_penalty=3.5,
    num_beams=4,
    early_stopping=True,
)
```

[Read the full model card (516 words)](https://savrn.com/models/led-large-book-summary/card)

## Configuration

Architecture

LEDForConditionalGeneration

Layers

12

Vocabulary size

50,265

Stored precision

float32

Model type

led

## Identity and Version

Repository

pszemraj/led-large-book-summary

Publisher

Peter Szemraj

Task

Summarization

Modality

Text

Library

transformers

Parameters

460M parameters

Languages

en

Revision

600de3bbcdb1da15fc4a5a2eb3ca7436eee25409

First published

2022-03-02

Last updated

2025-12-29

## Files and Weights

14 files, 3.7 GB in total. The weights are 2 files totalling 3.7 GB in bin, safetensors.

Weights2 files · 3.7 GB

Configuration4 files · 10.3 KB

Tokenizer4 files · 3.4 MB

Documentation2 files · 70.3 KB

Repository2 files · 1.2 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model.safetensors | Weights | 1.8 GB | 0ee872e86edb |
| pytorch_model.bin | Weights | 1.8 GB | 0603a70f1530 |
| config.json | Configuration | 1.4 KB | — |
| ds_config_zero2.json | Configuration | 895 B | — |
| special_tokens_map.json | Configuration | 772 B | — |
| trainer_state.json | Configuration | 7.2 KB | — |
| README.md | Documentation | 28.9 KB | — |
| evals-outputs/GAUNTLET.md | Documentation | 41.4 KB | — |
| .gitattributes | Repository | 1.2 KB | — |
| .gitignore | Repository | 13 B | — |
| merges.txt | Tokenizer | 456.4 KB | — |
| tokenizer.json | Tokenizer | 2.1 MB | — |
| tokenizer_config.json | Tokenizer | 1.3 KB | — |
| vocab.json | Tokenizer | 798.3 KB | — |

## License and Download

License

apache-2.0

Access

Open weights, no gate

Download size

3.7 GB

[Download from Peter Szemraj](https://huggingface.co/pszemraj/led-large-book-summary)

Released by Peter Szemraj through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0).

## Built From

- Described by arXiv:2105.08209
- Trained on (disclosed) kmfoda/booksum

## Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

| Benchmark | Conditions | Result | Reported by | Revision | Date |
| --- | --- | --- | --- | --- | --- |
| billsum | Configuration defaultTask SummarizationMetric ROUGE-1Comparison conditions not established | 40.5843 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| billsum | Configuration defaultTask SummarizationMetric ROUGE-2Comparison conditions not established | 17.3401 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| billsum | Configuration defaultTask SummarizationMetric ROUGE-LComparison conditions not established | 25.1256 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| billsum | Configuration defaultTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 34.6619 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| billsum | Configuration defaultTask SummarizationMetric gen_lenComparison conditions not established | 163.939 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| billsum | Configuration defaultTask SummarizationMetric lossComparison conditions not established | 4.79266 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-1Comparison conditions not established | 32.8774 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-2Comparison conditions not established | 13.3706 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-LComparison conditions not established | 20.4365 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-LSUMComparison conditions not established | 30.4408 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric gen_lenComparison conditions not established | 181.833 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric lossComparison conditions not established | 5.34889 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| kmfoda/booksum | Configuration kmfoda--booksumTask SummarizationMetric ROUGE-1Comparison conditions not established | 31.7308 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| kmfoda/booksum | Configuration kmfoda--booksumTask SummarizationMetric ROUGE-2Comparison conditions not established | 5.3311 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| kmfoda/booksum | Configuration kmfoda--booksumTask SummarizationMetric ROUGE-LComparison conditions not established | 16.1465 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| kmfoda/booksum | Configuration kmfoda--booksumTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 29.0883 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| kmfoda/booksum | Configuration kmfoda--booksumTask SummarizationMetric gen_lenComparison conditions not established | 154.904 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| kmfoda/booksum | Configuration kmfoda--booksumTask SummarizationMetric lossComparison conditions not established | 4.81571 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| multi_news | Configuration defaultTask SummarizationMetric ROUGE-1Comparison conditions not established | 39.0834 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| multi_news | Configuration defaultTask SummarizationMetric ROUGE-2Comparison conditions not established | 11.4043 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| multi_news | Configuration defaultTask SummarizationMetric ROUGE-LComparison conditions not established | 19.1813 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| multi_news | Configuration defaultTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 35.1581 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| multi_news | Configuration defaultTask SummarizationMetric gen_lenComparison conditions not established | 186.249 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| multi_news | Configuration defaultTask SummarizationMetric lossComparison conditions not established | 4.65491 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-1Comparison conditions not established | 33.4484 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-2Comparison conditions not established | 10.4249 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-LComparison conditions not established | 24.5802 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 29.8226 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric gen_lenComparison conditions not established | 65.4005 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric lossComparison conditions not established | 4.17608 | [pszemraj](https://huggingface.co/pszemraj/led-large-book-summary) Publisher reported | Evaluated revision not stated | — |

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 3.7 GB |
| 16-bit | 0.9 GB |
| 8-bit | 0.5 GB |
| 4-bit | 0.2 GB |

Weights only, from the published parameter count; the key-value cache and runtime add to this.

## Questions About led-large-book-summary

### How much GPU memory does led-large-book-summary need?

About 1.1 GB at 16-bit and 0.3 GB at 4-bit: the weights (460M parameters) plus a working margin. A long context needs more.

### What is the cheapest GPU to run led-large-book-summary on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

### Can I use led-large-book-summary commercially?

Yes. led-large-book-summary is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

## Similar Models

Model · Summarization

### [MEETING_SUMMARY](https://savrn.com/models/meeting-summary)

[Karthick Kaliannan Neelamohan](https://savrn.com/model-publishers/knkarthick)

Model obtained by Fine Tuning 'facebook/bart-large-xsum' using AMI Meeting Corpus, SAMSUM Dataset, DIALOGSUM Dataset, XSUM Dataset!

Open weights apache-2.0 406M parameters 1,024 tokens transformers

[View model](https://savrn.com/models/meeting-summary)

Model · Summarization

### [bart-large-cnn](https://savrn.com/models/bart-large-cnn)

[AI at Meta](https://savrn.com/model-publishers/facebook)

BART model pre-trained on English language, and fine-tuned on CNN Daily Mail. It was introduced in the paper BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension by Lewis et al. and first released in this repository (https://github.com/pytorch/fairseq/tree/master/examples/bart). Disclaimer: The team releasing BART did not write a model card for this model so this model card has been written by the Hugging Face team. BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function…

Open weights mit 406M parameters 1,024 tokens transformers

[View model](https://savrn.com/models/bart-large-cnn)

Model · Summarization

### [financial-summarization-pegasus](https://savrn.com/models/financial-summarization-pegasus)

[Human centered summarization](https://savrn.com/model-publishers/human-centered-summarization)

This model was fine-tuned on a novel financial news dataset, which consists of 2K articles from Bloomberg, on topics such as stock, markets, currencies, rate and cryptocurrencies. It is based on the PEGASUS model and in particular PEGASUS fine-tuned on the Extreme Summarization (XSum) dataset: google/pegasus-xsum model. PEGASUS was originally proposed by Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu in PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. Note: This model serves as a base version. For an even more advanced model with significantly enhanced performance, please check out our advanced version on Rapid API. The advanced model offers more…

Open weights 569M parameters 512 tokens transformers

[View model](https://savrn.com/models/financial-summarization-pegasus)

Model · Summarization

### [mbart50-tradenewssum](https://savrn.com/models/mbart50-tradenewssum)

[Daria Lyutova](https://savrn.com/model-publishers/lyutovad)

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the TradeNewsSum dataset for multilingual abstractive summarization of foreign trade news in Russian and English. This is a multilingual summarization model trained on economic and foreign trade news in Russian and English. It is based on the facebook/mbart-large-50-many-to-many-mmt architecture and fine-tuned specifically for the task of generating concise, informative summaries for news articles in the domain of international trade. - Generating abstractive summaries of foreign trade-related news in Russian and English. - Assisting analysts and journalists working with economic content. - Could be integrated…

Open weights mit 611M parameters 1,024 tokens transformers

[View model](https://savrn.com/models/mbart50-tradenewssum)

Model · Summarization

### [distilbart-news-summarizer](https://savrn.com/models/distilbart-news-summarizer)

[Sachin Rao](https://savrn.com/model-publishers/sachin21112004)

Imagine you have a very long news article, and you want someone to read it and tell you the key points in just a few sentences. That's exactly what this model does! This model takes a long news article and turns it into a short, easy-to-read summary. - It writes back a 3-4 sentence summary that captures all the important information The special thing about this model is that it's: 1. Very accurate - It understands news writing style very well 2. Very fast - It works quickly even on regular computers (not just expensive AI servers) 3. Specialized in news - It was trained specifically on news articles, so it understands how journalists write 4. Good with financial news - It knows market…

Open weights agpl-3.0 306M parameters 1,024 tokens transformers

[View model](https://savrn.com/models/distilbart-news-summarizer)

Model · Summarization

### [rut5-base-summ](https://savrn.com/models/rut5-base-summ)

[Dmitry Balobin](https://savrn.com/model-publishers/d0rj)

Finetuned ai-forever/ruT5-base for text and dialogue summarization. All 'train' subsets was concatenated and shuffled with seed 1000 - 7. Train subset = 155678 rows. Evaluation on 10% of concatenated 'validation' subsets = 1458 rows. See WandB logs. See report at REPORT WIP.

Open weights 223M parameters transformers

[View model](https://savrn.com/models/rut5-base-summ)

## Peter Szemraj

[All models and datasets](https://savrn.com/model-publishers/pszemraj)

## Versions

- [600de3bbcdb1](https://savrn.com/models/led-large-book-summary/versions/600de3bbcdb1) · current 2026-09-18

## Explore More

- [All summarization models](https://savrn.com/models/tasks/summarization)
- [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0)
- [Model comparisons](https://savrn.com/models/comparisons)
- [The model directory](https://savrn.com/models)
- [Open model prices by host](https://savrn.com/ai-index/pricing/open-models)

## Source

- Repository metadata, read 2026-10-21.
- [Hugging Face record](https://huggingface.co/pszemraj/led-large-book-summary)
- [How the hub is built](https://savrn.com/model-hub/methodology)