Downloads · 30 days
75
33% of all-time downloads
polish-text-summarizer
PiotrWarzachowski/polish-text-summarizer
polish-text-summarizer is a summarization model from PiotrWarzachowski. Use it when you need a shorter version of a longer text. The card lists the license as apache-2.0.
FLAN-T5-base fine-tuned for Polish text summarization.
All-time downloads
226
Public
Parameters
248M
5.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt4 GB · 57%
At a glance
- Task
- Summarization
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Feb 4, 2026
- Updated
- Feb 4, 2026
- SHA
- 9991c019
Model card
From the Hugging Face model README
Polish Text Summarizer
FLAN-T5-base fine-tuned for Polish text summarization.
Model Details
- Base model: google/flan-t5-base (248M parameters)
- Task: Text summarization
- Language: Polish
- Dataset: allegro/summarization-polish-summaries-corpus
Usage
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("PiotrWarzachowski/polish-text-summarizer")
model = AutoModelForSeq2SeqLM.from_pretrained("PiotrWarzachowski/polish-text-summarizer")
article = "Twój długi artykuł po polsku..."
inputs = tokenizer(article, max_length=512, truncation=True, return_tensors="pt")
outputs = model.generate(**inputs, max_length=128, num_beams=4, no_repeat_ngram_size=3)
summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(summary)
Limitations
- Max input: 512 tokens (~2000-3000 characters)
- Max output: 128 tokens (~500 characters)
- Polish diacritics (ą, ę, ł, etc.) may be simplified to ASCII equivalents
Training
- Optimizer: Adafactor
- Batch size: 1 (with gradient accumulation 8)
- Epochs: 3
- Learning rate: 1e-4
- Task
- Summarization
- Type
- t5
- License
- apache-2.0
- Languages
- pl
- Created
- Feb 4, 2026
- Updated
- Feb 4, 2026