SciFive-base-Pubmed_PMC Open-source Model - Empowering Biomedical Literature Text Conversion Research

Scifive Base Pubmed PMC

Developed by razent

SciFive is a text-to-text transfer model specifically designed for biomedical literature, trained on PubMed and PMC open-access journal full-text databases.

Large Language Model English#Biomedical Text Generation #PubMed/PMC Pretraining #Medical Literature QA

Downloads 754

Release Time : 3/2/2022

Model Overview

This model is primarily used for text tasks in the biomedical field, such as text classification, question-answering systems, and text generation.

Model Features

Biomedical Domain Specialization

Optimized specifically for biomedical literature with outstanding performance in this field

Multi-task Processing Capability

Capable of handling multiple text tasks including classification, QA, and generation

Large-scale Training Data

Trained on PubMed and PMC open-access journal full-text databases

Model Capabilities

Biomedical text classification

Biomedical question-answering systems

Biomedical text generation

Biomedical literature summarization

Use Cases

Medical Research

Literature Summarization

Automatically generate summaries of biomedical literature

Improves researchers' literature reading efficiency

Medical QA System

Answer biomedical-related questions

Assists medical research and clinical decision-making

Academic Research

Literature Classification

Automatically classify biomedical literature

Enhances literature management and retrieval efficiency

🚀 SciFive Pubmed+PMC Base

SciFive Pubmed+PMC Base is a text - to - text transformer model for biomedical literature, which can be applied to various NLP tasks such as token - classification, text - classification, etc.

🚀 Quick Start

This section provides a brief guide on how to use the SciFive Pubmed+PMC Base model. For more detailed information, please refer to our Github repo.

✨ Features

Multiple NLP Tasks: It supports tasks like token - classification, text - classification, question - answering, text2text - generation, and text - generation.
Trained on Biomedical Datasets: The model is trained on datasets including pubmed and pmc/open_access.

📦 Installation

The installation steps are not provided in the original README. If you need to use the model, you can follow the general installation process of Hugging Face models as shown in the usage example.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("razent/SciFive-base-Pubmed_PMC")  
model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-base-Pubmed_PMC")

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)

📚 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

Property	Details
Tags	token - classification, text - classification, question - answering, text2text - generation, text - generation
Datasets	pubmed, pmc/open_access

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