| license: apache-2.0 | |
| tags: | |
| - summarization | |
| - arabic | |
| - mbart | |
| - bayan10 | |
| library_name: transformers | |
| # Bayan Arabic Summarization Model | |
| This repository contains the summarization checkpoint used by Bayan. | |
| ## Recommended generation settings | |
| Use the following defaults for the best balance of faithfulness and brevity: | |
| ```python | |
| summary = model.generate( | |
| **inputs, | |
| max_new_tokens=40, | |
| num_beams=1, | |
| do_sample=False, | |
| early_stopping=False, | |
| no_repeat_ngram_size=3, | |
| repetition_penalty=1.1, | |
| ) | |
| ``` | |
| ## Notes | |
| - The checkpoint is optimized for Arabic news-style summarization. | |
| - Beam search and sampling may increase hallucination on some inputs. | |
| - If a summary drifts too far from the source, prefer a more extractive fallback. | |