This checkpoint should be loaded into BartForConditionalGeneration.frompretrained. See the BART docs for more information.
Open-weight model · Summarization
Text-Summarizer-t5-small-ONNX
by ONNX Community onnx-community/Text-Summarizer-t5-small-ONNX
This is an ONNX version of UX4567/Text-Summarizer-t5-small. It was automatically converted and uploaded using this Hugging Face Space.
Parameters—
Context—
Weights2.1 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
This is an ONNX version of UX4567/Text-Summarizer-t5-small. It was automatically converted and uploaded using this Hugging Face Space. See the pipeline documentation for summarization: https://huggingface.co/docs/transformers.js/api/pipelines#modulepipelines.SummarizationPipeline This model is a fine-tuned version of T5 designed for abstractive text summarization. It condenses long articles, documents, or paragraphs into short, accurate, and context-aware summaries. You can load and test the model using the Hugging Face transformers pipeline or direct model classes: from transformers import pipeline summarizer = pipeline("text-generation", model="UX4567/Text-Summarizer-t5-small") text = """…
Excerpt from the card by ONNX Community.
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 32,128
- Model type
- t5
Identity and Version
- Repository
- onnx-community/Text-Summarizer-t5-small-ONNX
- Publisher
- ONNX Community
- Task
- Summarization
- Modality
- Text
- Library
- transformers.js
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 6d4303b3fdd41cd5f568ddaed219c130ea4cebe2
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
19 files, 2.1 GB in total. The weights are 15 files totalling 2.1 GB in onnx.
Weights15 files · 2.1 GB
Configuration2 files · 1.7 KB
Documentation1 file · 1.9 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| onnx/decoder_model.onnx | Weights | 232.6 MB | 5348c68cef16 |
| onnx/decoder_model_bnb4.onnx | Weights | 89.5 MB | f5b7141d0f90 |
| onnx/decoder_model_merged.onnx | Weights | 195.9 MB | 56e5868667f7 |
| onnx/decoder_model_merged_bnb4.onnx | Weights | 84.6 MB | 0b2218ada6d4 |
| onnx/decoder_model_merged_int8.onnx | Weights | 196.1 MB | 0e940900ddea |
| onnx/decoder_model_merged_q4.onnx | Weights | 86.6 MB | e87c70fe5d60 |
| onnx/decoder_model_merged_quantized.onnx | Weights | 196.1 MB | 0e940900ddea |
| onnx/decoder_model_merged_uint8.onnx | Weights | 196.1 MB | 0e940900ddea |
| onnx/decoder_model_q4.onnx | Weights | 92.1 MB | dfc93986080d |
| onnx/decoder_with_past_model.onnx | Weights | 220.0 MB | f5656f0d0b91 |
| onnx/decoder_with_past_model_bnb4.onnx | Weights | 87.7 MB | d35ff3abdda9 |
| onnx/decoder_with_past_model_q4.onnx | Weights | 90.1 MB | ac0983a18591 |
| onnx/encoder_model.onnx | Weights | 141.5 MB | 26f62a3a0602 |
| onnx/encoder_model_bnb4.onnx | Weights | 76.6 MB | d292a4fc863f |
| onnx/encoder_model_q4.onnx | Weights | 77.8 MB | d2da8ab3b73d |
| config.json | Configuration | 1.5 KB | — |
| generation_config.json | Configuration | 142 B | — |
| README.md | Documentation | 1.9 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.1 GB
Download from ONNX Community
Released by ONNX Community through its official repository on Hugging Face.
Built From
- Derived from UX4567/Text-Summarizer-t5-small
- Quantized from UX4567/Text-Summarizer-t5-small
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.1 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 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…