KoAlpaca-Polyglot-5.8B Open-source Korean Language Model - Supports Diverse Korean Content Processing

Home

Koalpaca Polyglot 5.8B

Developed by beomi

Korean language model fine-tuned on the KoAlpaca v1.1b dataset based on polyglot-ko-5.8b

Large Language Model

Transformers

KoreanOpen Source License:Apache-2.0 #Korean text generation #Multi-turn dialogue #Instruction fine-tuning

Downloads 9,571

Release Time : 3/16/2023

Model Overview

This is a Korean-optimized language model based on EleutherAI's polyglot-ko-5.8b model fine-tuned on the KoAlpaca dataset, suitable for Korean text generation tasks.

Model Features

Korean optimization

Specially optimized and fine-tuned for Korean language characteristics

Large parameter size

With 5.8B parameters, it has strong language understanding and generation capabilities

KoAlpaca dataset fine-tuning

Fine-tuned on the KoAlpaca-v1.1b dataset, enhancing instruction-following capabilities

Model Capabilities

Korean text generation

Instruction following

Language understanding

Use Cases

Natural language processing

Korean chatbot

Building chatbots that can understand and communicate in Korean

Korean content generation

Automatically generating Korean articles, stories, or other text content

Property	Details
Model Type	Fine - tuned version of EleutherAI/polyglot - ko - 5.8b
Training Data	KoAlpaca - v1.1b
Tags	generated_from_trainer, polyglot - ko, gpt - neox, KoAlpaca
Pipeline Tag	text - generation
Base Model	EleutherAI/polyglot - ko - 5.8b

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

Koalpaca Polyglot 5.8B

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 KoAlpaca-Polyglot-5.8B (v1.1b)

🚀 Quick Start

✨ Features

📚 Documentation

Training procedure

Training hyperparameters

Framework versions

📄 License