---
language:
- en
license: mit
tags:
- summarization
- t5-large-summarization
- pipeline:summarization
model-index:
- name: sysresearch101/t5-large-finetuned-xsum
  results:
  - task:
      type: summarization
      name: Summarization
    dataset:
      name: xsum
      type: xsum
      config: default
      split: test
    metrics:
    - type: rouge
      value: 26.8921
      name: ROUGE-1
      verified: true
      verifyToken: >-
        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmFkMTFiNmM3YmRkZDk1Y2FhM2EwOTdiYmUwYjBhMGEzZmIyZmIwNWI5OTVmY2U0N2QzYzgxYzM0OTEzMjFjNSIsInZlcnNpb24iOjF9.fOq4zI_BWvTLFJFQOWNk3xEsDIu3aAeboGYPw5TiBqdJJjvdyKmLbfj2WVnNboWbrmp1PuL01iJjTi2Xj6PUAA
    - type: rouge
      value: 6.9411
      name: ROUGE-2
      verified: true
      verifyToken: >-
        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTBlZmI3NjQ3M2JiYzI4MTg3YmJkMjg0ZmE5MDUwNzljNTYyM2M0NzA3YTNiNTA2Nzk4MDhhYWZjZjgyMmE1MCIsInZlcnNpb24iOjF9.rH0DY2hMz2rXaK29vkt7xah-3G95rY4MOS2oVKjXmw4TijB-ZVytfLJAlBmyqA8HYAythRCywmLSjjCDWc66Cg
    - type: rouge
      value: 21.2832
      name: ROUGE-L
      verified: true
      verifyToken: >-
        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODAwZDYzNTc0NjZhNzNiMDE2ZDY2NjNjNmViNTc0NDVjNTZkYjljODhmYmNiMWFhY2NkZjU5MzQ0NmM0OTcyMSIsInZlcnNpb24iOjF9.5duHtdjZ8dwtbp1HKyMR4mVK9IIlEZvuWGjQMErpE7VNyKPhMOT6Avh_vXFQz6q_jBzqpZGGREho1mt50yBsDw
    - type: rouge
      value: 21.284
      name: ROUGE-LSUM
      verified: true
      verifyToken: >-
        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NmNhZTZmZDFkNTcyYjQ4MjhhYWJhODY1ZGRjODY2ZTE5MmRmZDRlYTk4NWE4YWM1OWY2M2NjOWQ3YzU0OCIsInZlcnNpb24iOjF9.SJ8xTcAVWrRDmJmQoxE1ADIcdGA4tr3V04Lv0ipMJiUksCdNC7FO8jYbjG9XmiqbDnnr5h4XoK4JB4-GsA-gDA
    - type: loss
      value: 2.5411810874938965
      name: loss
      verified: true
      verifyToken: >-
        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGViNTVlNGI0Njk4NmZmZjExNDBkNTQ4N2FhMzRkZjRjNDNlYzFhZDIyMjJhMmFiM2ZhMTQzYTM4YzNkNWVlNyIsInZlcnNpb24iOjF9.p9n2Kf48k9F9Bkk9j7UKRayvVmOr7_LV80T0ti4lUWFtTsZ91Re841xnEAcKSYgQ9-Bni56ldq9js3kunspJCw
    - type: gen_len
      value: 18.7755
      name: gen_len
      verified: true
      verifyToken: >-
        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQ1ZWUxNmFjNmU0OGI4MDQyZDNjMWQwZGViNDhlMzE1OGE3YmYwYzZjYmM1NWEwMjk2MDFiMjQ4ZThhMjg5YyIsInZlcnNpb24iOjF9.aNp-NFzBSm84GnXuDtYuHaOsSk7zw8kjCphowYFciwt-aDnhwwurYIr59kMT8JNFMnRInsDi8tvYdapareV3DA
datasets:
- EdinburghNLP/xsum
base_model:
- google-t5/t5-large
---

# T5-Large Fine-tuned on XSum

**Task:** Abstractive Summarization (English)  
**Base Model:** google-t5/t5-large  
**License:** MIT

## Overview

This model is a T5-Large checkpoint fine-tuned exclusively on the [XSum](https://huggingface.co/datasets/EdinburghNLP/xsum) dataset. It specializes in generating concise, single-sentence summaries in the style of BBC article abstracts.

## Performance ~ On XSum test set

| Metric | Score |
|--------|-------|
| ROUGE-1 | 26.89 |
| ROUGE-2 | 6.94  |
| ROUGE-L | 21.28 |
| Loss | 2.54 |
| Avg. Length | 18.77 tokens |


## Usage

### Quick Start

```python
from transformers import pipeline

summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum")

article = "Your article text here..."
summary = summarizer(article, max_length=80, min_length=20, do_sample=False)
print(summary[0]['summary_text'])
```

### Advanced Usage

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("sysresearch101/t5-large-finetuned-xsum")
model = AutoModelForSeq2SeqLM.from_pretrained("sysresearch101/t5-large-finetuned-xsum")

inputs = tokenizer("summarize: " + article, return_tensors="pt", max_length=512, truncation=True)
outputs = model.generate(
    **inputs,
    max_length=80,
    min_length=20,
    num_beams=4,
    no_repeat_ngram_size=2,
    length_penalty=1.0,
    repetition_penalty=2.5,
    use_cache=True,
    early_stopping=True
    do_sample = True,
    temperature = 0.8,
    top_k = 50,
    top_p = 0.95
)

summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
```

## Training Data

- [XSum](https://huggingface.co/datasets/EdinburghNLP/xsum): BBC articles paired with professionally written single-sentence summaries


## Intended Use

- **Primary:** Summarization
- **Secondary:** Research on extreme summarization, single-sentence summary generation, Educational demonstrations, comparative studies with multi-sentence models
- **Not recommended:** Multi-sentence summarization tasks, production use without validation

## Limitations
- Trained only on news domain; may not generalize to other text types
- Generates very short summaries (average ~19 tokens)
- May oversimplify complex topics due to single-sentence constraint


## Citation

```bibtex
@misc{stept2023_t5_large_xsum,
  author = {Shlomo Stept (sysresearch101)},
  title = {T5-Large Fine-tuned on XSum for Abstractive Summarization},
  year = {2023},
  publisher = {Hugging Face},
  url = {https://huggingface.co/sysresearch101/t5-large-finetuned-xsum}
}
```

## Papers Using This Model

* [Tam et al. (2023). *Evaluating the Factual Consistency of Large Language Models Through Summarization (FIB).* Findings of ACL 2023.](https://arxiv.org/pdf/2211.08412)
* [Liu et al. (2024). *LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores.* Findings of ACL 2024.](https://aclanthology.org/2024.findings-acl.753.pdf)
* [Zhu et al. (2024). *MTAS: A Reference-Free Approach for Evaluating Abstractive Summarization Systems.* Proceedings of the ACM on SE (FSE 2024).](https://doi.org/10.1145/3660820)


## Contact

Created by [Shlomo Stept](https://shlomostept.com) ([ORCID: 0009-0009-3185-589X](https://orcid.org/0009-0009-3185-589X))
DARMIS AI


- Website: [shlomostept.com](https://shlomostept.com)  
- LinkedIn: [linkedin.com/in/shlomo-stept](https://linkedin.com/in/shlomo-stept)