SciFive-large-Pubmed Open Source Model - Free for Biomedical Text Tasks

Scifive Large Pubmed

Developed by razent

SciFive is a text-to-text transformation model specifically designed for biomedical literature, based on the T5 architecture, focusing on handling text tasks in the biomedical field.

Large Language Model English#Biomedical Text Generation #PubMed Literature Processing #T5 Architecture Optimization

Downloads 63

Release Time : 3/2/2022

Model Overview

SciFive is a pre-trained model based on the T5 architecture, specifically optimized for biomedical literature. It can perform various text processing tasks, including text classification, Q&A systems, and text generation, making it particularly suitable for handling specialized content in the biomedical field.

Model Features

Specialized for Biomedical Field

Specifically trained and optimized for biomedical literature, capable of better understanding and processing professional medical terminology and concepts.

Multi-task Processing Capability

Capable of performing various text processing tasks, including classification, Q&A, and generation.

Based on T5 Architecture

Utilizes the advanced T5 text-to-text transformation architecture, featuring powerful sequence modeling capabilities.

Model Capabilities

Biomedical text classification

Biomedical Q&A system

Biomedical text generation

Biomedical literature summarization

Biomedical entity recognition

Use Cases

Medical Research

Literature Summarization

Automatically generate summaries for biomedical research papers

Helps researchers quickly grasp the main content of papers

Medical Q&A System

Answer questions about specific medical concepts or research

Provides accurate medical knowledge answers

Bioinformatics

Gene Research Assistance

Analyze and interpret gene-related research literature

Accelerates the gene research process

🚀 SciFive Pubmed Large

SciFive Pubmed Large is a text - to - text transformer model designed for various biomedical NLP tasks, leveraging the Pubmed dataset.

🚀 Quick Start

This model can be used for multiple natural language processing tasks in the biomedical field, such as token classification, text classification, question - answering, text2text generation, and text generation.

✨ Features

Task Versatility: Capable of handling token - classification, text - classification, question - answering, text2text - generation, and text - generation tasks.
Dataset - Based: Trained on the Pubmed dataset, making it suitable for biomedical literature processing.

📚 Documentation

Introduction

Paper: SciFive: a text - to - text transformer model for biomedical literature

Authors: Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan - Bonnet

How to use

For more details, do check out our Github repo.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("razent/SciFive-large-Pubmed")  
model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-large-Pubmed")

sentence = "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor ."
text =  sentence + " </s>"

encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")

outputs = model.generate(
    input_ids=input_ids, attention_mask=attention_masks,
    max_length=256,
    early_stopping=True
)

for output in outputs:
    line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
    print(line)

```markdown
| Property | Details |
|----------|---------|
| Tags | token - classification, text - classification, question - answering, text2text - generation, text - generation |
| Datasets | pubmed |

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご