A T5-small model fine-tuned on the CNN/DailyMail dataset for abstractive news summarization. Part of the TSUT (Text Summarization Using Transformers) research project comparing BART-large-CNN vs fine-tuned T5-small.

Model Details

Model type: T5-Small (Text-to-Text Transfer Transformer)
Base model: google-t5/t5-small (60M parameters)
Fine-tuned on: CNN/DailyMail 3.0.0
Task: Abstractive Text Summarization
Training epochs: 3
Hardware: NVIDIA Tesla T4 (Kaggle)
Developed by: Hardik Sonawane

How to Use

python

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("hardiksonawane/tsut-t5-finetuned")
model = AutoModelForSeq2SeqLM.from_pretrained("hardiksonawane/tsut-t5-finetuned")

text = "Your article text here..."
inputs = tokenizer("summarize: " + text, return_tensors="pt", max_length=512, truncation=True)
outputs = model.generate(inputs["input_ids"], max_length=130, min_length=30, do_sample=False)
summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(summary)