|
Download README.md from Hiratax/t5-news-summarizer: direct link, hf CLI and curl.
- Browser
- Download file 3.93 kB
-
https://huggingface.co/Hiratax/t5-news-summarizer/resolve/main/README.md
- Command line
-
hf download hf://Hiratax/t5-news-summarizer/README.md
-
curl -L -o README.md https://huggingface.co/Hiratax/t5-news-summarizer/resolve/main/README.md
3.93 kB
metadata
license: apache-2.0
tags:
- summarization
- news
- t5
- flan-t5
- generated_from_trainer
base_model: google/flan-t5-base
widget:
- text: >-
The James Webb Space Telescope (JWST) has captured a lush landscape of
stellar birth. The new image shows the Cosmic Cliffs, which are the edge
of a giant gaseous cavity within the star-forming region NGC 3324. The
cavity has been carved from the nebula by the intense ultraviolet
radiation and stellar winds from extremely massive, hot, young stars
located in the center of the bubble, above the area shown in this image.
example_title: James Webb Telescope
- text: >-
Russian President Vladimir Putin said that a US plan to end the war in
Ukraine could 'form the basis for future agreements' but renewed threats
to seize more territory by force unless Kyiv withdraws. Speaking to
reporters in Bishtek, Putin confirmed the Kremlin was expecting a US
delegation headed by Special Envoy Steve Witkoff to visit Moscow early
next week.
example_title: Ukraine Conflict
inference:
parameters:
max_length: 150
min_length: 40
length_penalty: 2
num_beams: 4
T5-Base News Summarizer (Multi-Style)
This model is a fine-tuned version of google/flan-t5-base trained on samples from CNN/DailyMail and XSum.
It generates news summaries in three styles: Harsh (Concise), Standard, and Detailed.
Model Description
- Model Type: Sequence-to-Sequence Transformer (T5)
- Language: English
- Base Model:
google/flan-t5-base - Training Data: ~9k mixed samples from CNN/DailyMail & XSum
Key Features
This model supports a Style Prompt that determines summary length and density:
Harsh
- Very concise
- Headline-like
- Trained mostly on XSum
Standard
- Balanced, general-purpose summarization
Detailed
- Longer, more contextual summaries
- Trained with CNN/DailyMail
Usage
from transformers import pipeline
summarizer = pipeline("summarization", model="Hiratax/t5-news-summarizer")
text = """
The James Webb Space Telescope (JWST) has captured a lush landscape of stellar birth.
The new image shows the Cosmic Cliffs, which are the edge of a giant gaseous cavity within the star-forming region NGC 3324.
"""
# 1. Standard
print(summarizer("summarize standard: " + text))
# 2. Harsh (Headline)
print(summarizer("summarize harsh: " + text))
# 3. Detailed
print(summarizer("summarize detailed: " + text))
Recommended Inference Parameters
| Style | Min Length | Max Length | Length Penalty | Repetition Penalty | N-Gram Block |
|---|---|---|---|---|---|
| Harsh | 10 | 35% of input | 1.0 | 2.0 | 3 |
| Standard | 60 | 150 | 2.0 | 1.5 | 3 |
| Detailed | 50% input | 150% of input | 1.5 | 1.2 | 4 |
Tip:
"Detailed" style benefits from no_repeat_ngram_size=4 to avoid repeated openings.
Training Procedure
Hyperparameters
- Epochs: 8
- Learning Rate: 1e-4
- Batch Size: 4
- Gradient Accumulation: 2
- Weight Decay: 0.01
- Optimizer: AdamW
- Precision: FP16
Data Strategy
- Harsh → XSum (abstractive, short)
- Detailed → CNN/DailyMail (longer, higher detail)
- Safety: Removed cases where summary > article length to reduce hallucinations
Limitations
- May occasionally output the typo "occupys" (training noise).
- Max input length: 512 tokens (longer text is truncated).
- Model performance decreases on extremely long or highly technical articles.
License
Apache 2.0