YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
🇮🇳 mBART Tamil ReadSum — Readability-Aware Summarizer
LoRA fine-tune of
facebook/mbart-large-50for readability-controlled Tamil story summarization.
This model generates abstractive Tamil summaries at three readability levels — Simple (எளிது), Moderate (சராசரி), and Complex (இலக்கியம்) — using control tokens prepended to the source text.
📊 Model Details
| Property | Value |
|---|---|
| Base model | facebook/mbart-large-50 |
| Fine-tune method | LoRA (PEFT) → Merged |
| LoRA rank (r) | 16 |
| LoRA alpha | 32 |
| Trainable parameters | ~1.4% of base (≈8.6M / 611M) |
| Task | Sequence-to-Sequence Summarization |
| Languages | Tamil (ta_IN) → Tamil (ta_IN) |
| Best BERTScore F1 | 0.8747 |
| Best epoch | 19 |
| Model size | ~2.4 GB |
🚀 How to Use
Requirements
pip install transformers sentencepiece torch
Model tree for SindhuBharathi/mBART_tamil_readsum_best
Base model
facebook/mbart-large-50