This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
Open-weight model · Summarization
mT5_multilingual_XLSum
by BUET CSE NLP Group csebuetnlp/mT5_multilingual_XLSum
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.
Parameters—
Context—
Weights2.3 GB
License—
AccessOpen weights
Monthly Downloads13.6k
Model Card
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…
Excerpt from the card by BUET CSE NLP Group.
Configuration
- Architecture
- MT5ForConditionalGeneration
- Vocabulary size
- 250,112
- Model type
- mt5
Identity and Version
- Repository
- csebuetnlp/mT5_multilingual_XLSum
- Publisher
- BUET CSE NLP Group
- Task
- Summarization
- Modality
- Text
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- am, ar, az, bn, my, zh, en, fr
- Revision
- 2437a524effdbadc327ced84595508f1e32025b3
- First published
- 2022-03-02
- Last updated
- 2022-08-13
Files and Weights
7 files, 2.3 GB in total. The weights are 1 file totalling 2.3 GB in bin.
Weights1 file · 2.3 GB
Configuration2 files · 795 B
Tokenizer2 files · 4.3 MB
Documentation1 file · 7.4 KB
Repository1 file · 737 B
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pytorch_model.bin | Weights | 2.3 GB | 1899a041acee |
| config.json | Configuration | 730 B | — |
| special_tokens_map.json | Configuration | 65 B | — |
| README.md | Documentation | 7.4 KB | — |
| .gitattributes | Repository | 737 B | — |
| spiece.model | Tokenizer | 4.3 MB | ef78f86560d8 |
| tokenizer_config.json | Tokenizer | 375 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.3 GB
Download from BUET CSE NLP Group
Released by BUET CSE NLP Group through its official repository on Hugging Face.
Built From
- Trained on (disclosed) csebuetnlp/xlsum
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 |
|---|---|---|---|---|---|
| xsum | Configuration defaultTask SummarizationMetric ROUGE-1Comparison conditions not established | 36.5002 | csebuetnlp Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-2Comparison conditions not established | 13.934 | csebuetnlp Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-LComparison conditions not established | 28.9876 | csebuetnlp Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric ROUGE-LSUMComparison conditions not established | 28.9958 | csebuetnlp Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric gen_lenComparison conditions not established | 26.9733 | csebuetnlp Publisher reported |
Evaluated revision not stated | — |
| xsum | Configuration defaultTask SummarizationMetric lossComparison conditions not established | 2.06748 | csebuetnlp Publisher reported |
Evaluated revision not stated | — |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Similar Models
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…
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 checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.