This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
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.
Parameters—
Context512
Weights6.8 GB
License—
AccessOpen weights
Monthly Downloads229.2k
Model Card
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…
Excerpt from the card by Google.
Configuration
- Architecture
- PegasusForConditionalGeneration
- Context length (tokens)
- 512
- Layers
- 16
- Vocabulary size
- 96,103
- Model type
- pegasus
Identity and Version
- Repository
- google/pegasus-xsum
- Publisher
- Task
- Summarization
- Modality
- Text
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 8d8ffc158a3bee9fbb03afacdfc347c823c5ec8b
- First published
- 2022-03-02
- Last updated
- 2023-01-24
Files and Weights
12 files, 9.1 GB in total. The weights are 3 files totalling 6.8 GB in bin, h5, msgpack.
Weights3 files · 6.8 GB
Configuration3 files · 1.7 KB
Tokenizer3 files · 5.4 MB
Documentation1 file · 5.4 KB
Other1 file · 2.3 GB
Repository1 file · 391 B
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| flax_model.msgpack | Weights | 2.3 GB | ab6a33c8bbb3 |
| pytorch_model.bin | Weights | 2.3 GB | f19169fbf6d5 |
| tf_model.h5 | Weights | 2.3 GB | 4411d0ec75cc |
| config.json | Configuration | 1.4 KB | — |
| generation_config.json | Configuration | 259 B | — |
| special_tokens_map.json | Configuration | 65 B | — |
| README.md | Documentation | 5.4 KB | — |
| tf_weights_dict.pkl | Other | 2.3 GB | e114926c773d |
| .gitattributes | Repository | 391 B | — |
| spiece.model | Tokenizer | 1.9 MB | — |
| tokenizer.json | Tokenizer | 3.5 MB | — |
| tokenizer_config.json | Tokenizer | 87 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 6.8 GB
Download from Google
Released by Google through its official repository on Hugging Face.
Built From
- Described by arXiv:1912.08777
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 |
|---|---|---|---|---|---|
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-1Comparison conditions not established | 22.2062 | google Publisher reported |
Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-2Comparison conditions not established | 7.6701 | google Publisher reported |
Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-LComparison conditions not established | 15.4046 | google Publisher reported |
Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric ROUGE-LSUMComparison conditions not established | 19.2182 | google Publisher reported |
Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric gen_lenComparison conditions not established | 25.0234 | google Publisher reported |
Evaluated revision not stated | — |
| cnn_dailymail | Configuration 3.0.0Task SummarizationMetric lossComparison conditions not established | 2.68124 | google Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-1Comparison conditions not established | 21.8096 | google Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-2Comparison conditions not established | 4.2525 | google Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-LComparison conditions not established | 17.4469 | google Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 18.8907 | google Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric gen_lenComparison conditions not established | 20.3122 | google Publisher reported |
Evaluated revision not stated | — |
| samsum | Configuration samsumTask SummarizationMetric lossComparison conditions not established | 3.03172 | google Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-1Comparison conditions not established | 46.8623 | google Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-2Comparison conditions not established | 24.4533 | google Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-LComparison conditions not established | 39.0548 | google Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 39.0994 | google Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric gen_lenComparison conditions not established | 22.8821 | google Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric lossComparison conditions not established | 1.5717 | google Publisher reported |
Evaluated revision not stated | — |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About pegasus-xsum
What is pegasus-xsum's context length?
512 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
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…
This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.