Add model card

README.md

@@ -0,0 +1,54 @@
+---
+language:
+- pl
+license: apache-2.0
+tags:
+- summarization
+- polish
+- flan-t5
+- text2text-generation
+datasets:
+- allegro/summarization-polish-summaries-corpus
+pipeline_tag: summarization
+---
+
+# 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
+
+```python
+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