BEASTBOYJAY/my-fine-tuned-summarizer

Model Card for Model ID

Model Details

Model Description

This is the model is used for making or generating summary of the provided paragraph.

• Developed by: BEASTBOYJAY
• Model type: Transformer(encoder)
• Language(s) (NLP): English
• Finetuned from model: Bert-base-uncased

Uses

• For the summarization purpose only

Bias, Risks, and Limitations

This model is fine-tuned on very small dataset can need more fine-tuning for better results.(Fine-tuned this model only for eductional purposes)

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import EncoderDecoderModel, BertTokenizer

class TextSummarizer:
    def __init__(self, model_path, tokenizer_name="bert-base-uncased"):
        self.tokenizer = BertTokenizer.from_pretrained(tokenizer_name)
        self.model = EncoderDecoderModel.from_pretrained(model_path)

    def summarize(self, text, max_input_length=512):
        inputs = self.tokenizer(
            text,
            return_tensors="pt",
            truncation=True,
            padding="max_length",
            max_length=max_input_length,
        )
        summary_ids = self.model.generate(
            inputs["input_ids"],
            attention_mask=inputs["attention_mask"],
            decoder_start_token_id=self.tokenizer.cls_token_id,
            max_length=128,
            num_beams=4,
            length_penalty=1.5,
            no_repeat_ngram_size=1,
            early_stopping=True,
        )
        summary = self.tokenizer.decode(summary_ids[0], skip_special_tokens=True)
        return summary


if __name__ == "__main__":
    summarizer = TextSummarizer(model_path="BEASTBOYJAY/my-fine-tuned-summarizer")
    test_article = "Your article or paragraph"
    summary = summarizer.summarize(test_article)
    print("Generated Summary:", summary)