distilbart-cnn-6-6 by Joshua: Open-Weight Model

Model Card

By Joshua, published under apache-2.0, revision 6b476295a3cf.

https://huggingface.co/sshleifer/distilbart-cnn-6-6 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Read Joshua's full model card

https://huggingface.co/sshleifer/distilbart-cnn-6-6 with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

Example: Summarization.

import { pipeline } from '@huggingface/transformers';

const generator = await pipeline('summarization', 'Xenova/distilbart-cnn-6-6');
const text = 'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, ' +
  'and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. ' +
  'During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest ' +
  'man-made structure in the world, a title it held for 41 years until the Chrysler Building in New ' +
  'York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to ' +
  'the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the ' +
  'Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second ' +
  'tallest free-standing structure in France after the Millau Viaduct.';
const output = await generator(text, {
  max_new_tokens: 100,
});

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Configuration

Architecture: BartForConditionalGeneration
Context length (tokens): 1,024
Layers: 6
Vocabulary size: 50,264
Model type: bart

Identity and Version

Repository: Xenova/distilbart-cnn-6-6
Publisher: Joshua
Task: Summarization
Modality: Text
Library: transformers.js
Parameters: Not stated by the source
Languages: Not stated by the source
Revision: 6b476295a3cf27d5b20e8c8b847a54ab8e5d0df9
First published: 2023-05-02
Last updated: 2025-07-22

Files and Weights

42 files, 7.9 GB in total. The weights are 32 files totalling 7.9 GB in onnx.

Weights32 files · 7.9 GB

Configuration4 files · 6.3 KB

Tokenizer4 files · 3.4 MB

Documentation1 file · 1.9 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
onnx/decoder_model.onnx	Weights	613.7 MB	3b2ceb285d8c
onnx/decoder_model_bnb4.onnx	Weights	267.5 MB	0bd965c68e7e
onnx/decoder_model_fp16.onnx	Weights	306.9 MB	4230de4d6895
onnx/decoder_model_int8.onnx	Weights	154.0 MB	bbffe6cd1b1b
onnx/decoder_model_merged.onnx	Weights	613.9 MB	32a8b5910c88
onnx/decoder_model_merged_bnb4.onnx	Weights	268.0 MB	97855771dae4
onnx/decoder_model_merged_fp16.onnx	Weights	307.3 MB	8156d8f2c5f8
onnx/decoder_model_merged_int8.onnx	Weights	154.6 MB	83d1e5f1fdd5
onnx/decoder_model_merged_q4.onnx	Weights	274.3 MB	3c71d077e6fa
onnx/decoder_model_merged_q4f16.onnx	Weights	162.6 MB	8db838d8fede
onnx/decoder_model_merged_quantized.onnx	Weights	155.1 MB	7a584dce621f
onnx/decoder_model_merged_uint8.onnx	Weights	154.6 MB	041de5b4af07
onnx/decoder_model_q4.onnx	Weights	273.8 MB	52823c5aeb70
onnx/decoder_model_q4f16.onnx	Weights	162.2 MB	ebcba13714f4
onnx/decoder_model_quantized.onnx	Weights	154.7 MB	034156c203b0
onnx/decoder_model_uint8.onnx	Weights	154.0 MB	9d6bf6bd9389
onnx/decoder_with_past_model.onnx	Weights	563.3 MB	009480ed2abb
onnx/decoder_with_past_model_bnb4.onnx	Weights	260.3 MB	2347c236a526
onnx/decoder_with_past_model_fp16.onnx	Weights	281.6 MB	52b81508257b
onnx/decoder_with_past_model_int8.onnx	Weights	141.3 MB	d36a5f736287
onnx/decoder_with_past_model_q4.onnx	Weights	265.8 MB	451bb022f5c5
onnx/decoder_with_past_model_q4f16.onnx	Weights	155.0 MB	327bd2bbfd6a
onnx/decoder_with_past_model_quantized.onnx	Weights	142.0 MB	58a6832ec3a2
onnx/decoder_with_past_model_uint8.onnx	Weights	141.3 MB	146dfa37f4d4
onnx/encoder_model.onnx	Weights	512.5 MB	1ce28b2b7a99
onnx/encoder_model_bnb4.onnx	Weights	253.0 MB	59af5674b826
onnx/encoder_model_fp16.onnx	Weights	256.4 MB	97513911d103
onnx/encoder_model_int8.onnx	Weights	128.5 MB	50e6d1485f73
onnx/encoder_model_q4.onnx	Weights	257.7 MB	2bab6f564e9f
onnx/encoder_model_q4f16.onnx	Weights	147.8 MB	525395335b3d
onnx/encoder_model_quantized.onnx	Weights	128.8 MB	14d9b2d8fb1b
onnx/encoder_model_uint8.onnx	Weights	128.5 MB	22c79187b8b0
config.json	Configuration	1.9 KB	—
generation_config.json	Configuration	363 B	—
quantize_config.json	Configuration	3.1 KB	—
special_tokens_map.json	Configuration	957 B	—
README.md	Documentation	1.9 KB	—
.gitattributes	Repository	1.5 KB	—
merges.txt	Tokenizer	456.3 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: 7.9 GB

Download from Joshua

Released by Joshua through its official repository on Hugging Face. Read the license.

Built From

Derived from sshleifer/distilbart-cnn-6-6
Quantized from sshleifer/distilbart-cnn-6-6

Memory Requirements

Precision	Weights in memory
As published	7.9 GB

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

Questions About distilbart-cnn-6-6

Can I use distilbart-cnn-6-6 commercially?

Yes. distilbart-cnn-6-6 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.

What is distilbart-cnn-6-6's context length?

1,024 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Summarization

distilbart-cnn-12-6

Sam Shleifer

This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.

Open weights apache-2.0 1,024 tokens transformers

View model

Model · Summarization

pegasus-xsum

Google

Original TF 1 code here Authors: Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu on Dec 18, 2019 The following is copied from the authors' README. We train a pegasus model with sampled gap sentence ratios on both C4 and HugeNews, and stochastically sample important sentences. The updated the results are reported in this table. The "Mixed & Stochastic" model has the following changes: - trained on both C4 and HugeNews (dataset mixture is weighted by their number of examples). - trained for 1.5M instead of 500k (we observe slower convergence on pretraining perplexity). - the model uniformly sample a gap sentence ratio between 15% and 45%. - importance sentences are sampled using a…

Open weights 512 tokens transformers

View model

Model · Summarization

bart-large-cnn-samsum

Philipp Schmid

This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.

Open weights mit 1,024 tokens transformers

View model

Model · Summarization

distilbart-xsum-12-6

Sam Shleifer

This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.

Open weights apache-2.0 1,024 tokens transformers

View model

Model · Summarization

t5-small-booksum

Cosmina Nicu

Open weights mit transformers

View model

Model · Summarization

mT5_multilingual_XLSum

BUET CSE NLP Group

This repository contains the mT5 checkpoint finetuned on the 45 languages of XL-Sum dataset. For finetuning details and scripts, see the paper and the official repository. Scores on the XL-Sum test sets are as follows: Language | ROUGE-1 / ROUGE-2 / ROUGE-L Amharic | 20.0485 / 7.4111 / 18.0753 Arabic | 34.9107 / 14.7937 / 29.1623 Azerbaijani | 21.4227 / 9.5214 / 19.3331 Bengali | 29.5653 / 12.1095 / 25.1315 Burmese | 15.9626 / 5.1477 / 14.1819 Chinese (Simplified) | 39.4071 / 17.7913 / 33.406 Chinese (Traditional) | 37.1866 / 17.1432 / 31.6184 English | 37.601 / 15.1536 / 29.8817 French | 35.3398 / 16.1739 / 28.2041 Gujarati | 21.9619 / 7.7417 / 19.86 Hausa | 39.4375 / 17.6786 / 31.6667…

Open weights transformers

View model