Views
No views yet
genre: → classify the genre of a bookrating: → predict the numeric ratingtitle: → generate a book title1from transformers import T5Tokenizer, T5ForConditionalGeneration
2
3model = T5ForConditionalGeneration.from_pretrained("AbrarFahim75/t5-multitask-book")
4tokenizer = T5Tokenizer.from_pretrained("AbrarFahim75/t5-multitask-book")
5
6input_text = "genre: A dark and stormy night in an abandoned castle."
7inputs = tokenizer(input_text, return_tensors="pt")
8outputs = model.generate(**inputs)
9print(tokenizer.decode(outputs[0], skip_special_tokens=True))title, description, genre, rating"genre: <desc>""rating: <desc>""title: <desc>"| Task | Metric | Value (sample, dev split) |
|---|---|---|
| Genre Classification | Accuracy | ~0.78 (sample set) |
| Rating Prediction | RMSE | ~0.42 |
| Title Generation | BLEU | ~15.3 |
⚠️ These are informal evaluations using validation slices from the dataset.
1@misc{fahim2025t5bookmultitask,
2 title={T5 Multitask for Book Tasks},
3 author={Md Abrar Fahim},
4 year={2025},
5 url={https://huggingface.co/AbrarFahim75/t5-multitask-book}
6}