KoAlpaca-Polyglot-12.8B: Open Source Multilingual Korean Generation Model

Koalpaca Polyglot 12.8B

Developed by beomi

A multilingual Korean text generation model fine-tuned on the Korean Alpaca dataset v1.1b based on EleutherAI/polyglot-ko-12.8b

Large Language Model

Transformers

KoreanOpen Source License:Apache-2.0 #Korean text generation #Multilingual large model #GPT-NeoX architecture

Downloads 3,998

Release Time : 4/18/2023

Model Overview

This is a multilingual large language model supporting Korean, focusing on text generation tasks, suitable for Korean-related natural language processing applications

Model Features

Korean language optimization

Specially fine-tuned for Korean, delivering superior performance in Korean text generation tasks

Multi-GPU training

Distributed training using 4 A100 80G GPUs, improving training efficiency

Large parameter scale

12.8B parameter scale, providing stronger language understanding and generation capabilities

Model Capabilities

Korean text generation

Multilingual text processing

Dialogue system construction

Use Cases

Natural language processing

Korean chatbot

Building fluent Korean dialogue systems

Korean content creation

Automatically generating Korean articles, stories, and other content

Property	Details
Model Type	Fine - tuned model based on EleutherAI/polyglot-ko-12.8b
Training Data	KoAlpaca-v1.1b
Pipeline Tag	Text Generation
Base Model	EleutherAI/polyglot-ko-12.8b

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 12.8B

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 KoAlpaca-Polyglot-12.8B (v1.1b)

📚 Documentation

📋 Model Information

🔧 Technical Details

Training hyperparameters

Framework versions

📄 License