Llama-3-Open-Ko-8B-gguf Open Source Korean Language Model - Massive Data Training Empowers Language Interaction

Llama 3 Open Ko 8B Gguf

Developed by teddylee777

A Korean language model continuously pre-trained on the Llama-3-8B framework, trained with over 60GB of deduplicated text data

Large Language Model Supports Multiple Languages#Korean optimization #Multi-turn dialogue #Long text generation

Downloads 7,211

Release Time : 4/24/2024

Model Overview

Llama-3-Open-Ko-8B is a language model continuously pre-trained on the Llama-3-8B framework, focusing on Korean text generation and understanding

Model Features

Korean optimization

Specifically pre-trained for Korean, using the new Llama-3 tokenizer to process over 17.7 billion tokens

Long context support

Supports 8k context length, suitable for long-text tasks

Efficient inference

Uses GQA (Grouped Query Attention) technology to improve inference efficiency

Model Capabilities

Korean text generation

English text generation

Code generation

Dialogue system

Use Cases

Dialogue system

Smart assistant

Building a Korean intelligent dialogue assistant

Provides helpful, detailed, and polite responses

Content generation

Korean content creation

Generating Korean articles, stories, and other content

🚀 Llama-3-Open-Ko-8B

This project provides a quantized version of the Llama-3-Open-Ko-8B model, which is based on the Llama-3 framework and optimized for Korean language tasks.

🚀 Quick Start

Ollama

The following is the Modelfile for Ollama:

FROM Llama-3-Open-Ko-8B-Q8_0.gguf

TEMPLATE """{{- if .System }}
<s>{{ .System }}</s>
{{- end }}
<s>Human:
{{ .Prompt }}</s>
<s>Assistant:
"""

SYSTEM """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."""

PARAMETER temperature 0
PARAMETER num_predict 3000
PARAMETER num_ctx 4096
PARAMETER stop <s>
PARAMETER stop </s>

Update @ 2024.04.24: Release Llama-3-Open-Ko-8B model & Llama-3-Open-Ko-8B-Instruct-preview

✨ Features

The original model is beomi/Llama-3-Open-Ko-8B.
Quantized using llama.cpp.

📚 Documentation

Model Details

Property	Details
Model Type	Llama-3-Open-Ko-8B is a continued pretrained language model based on the Llama-3-8B framework. Llama-3-Open-Ko-8B-Instruct-preview incorporates concepts from the Chat Vector paper. Meta Llama 3 is developed and released by Meta.
Training Data	Same as Open-Solar-Ko Dataset. The Llama-3-Open-Ko model is trained with over 60GB of deduplicated texts sourced from publicly available resources.
Params	8B
Context length	8k
GQA	Yes
Token count	17.7B+
Knowledge cutoff	Jun, 2023
Model Developers	Junbum Lee (Beomi)
Variations	Llama-3-Open-Ko is available in one configuration — 8B.
Input/Output	Models accept text input and generate text and code.
Model Architecture	Llama 3 utilizes an optimized transformer architecture.

*Dataset list available here

Intended Use

Commercial and Research Applications: Llama 3 is designed for use in English, tailored for assistant-like chat in its instruction-tuned models, while the pretrained models are versatile across various natural language generation tasks.
Out-of-scope: Any use violating applicable laws, regulations, or the Acceptable Use Policy and Llama 3 Community License is prohibited.

Responsibility & Safety

Meta's commitment to Responsible AI includes steps to limit misuse and harm while supporting the open source community. Developers are encouraged to implement safety best practices and use resources like Meta Llama Guard 2 and Code Shield to tailor safety needs specifically to their use cases.

Responsible Release

Following a rigorous process against misuse, we ensure all safety and ethical guidelines are adhered to, as detailed in our Responsible Use Guide.

Ethical Considerations and Limitations

Llama 3 is built on the principles of openness, inclusivity, and helpfulness, designed to be accessible and valuable across diverse backgrounds and use cases. Developers should undertake thorough safety testing and tuning for specific applications before deployment.

Citation instructions

Llama-3-Open-Ko

@article{llama3openko,
  title={Llama-3-Open-Ko},
  author={L, Junbum},
  year={2024},
  url={https://huggingface.co/beomi/Llama-3-Open-Ko-8B}
}

Original Llama-3

@article{llama3modelcard,
  title={Llama 3 Model Card},
  author={AI@Meta},
  year={2024},
  url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}

License

The model is released under the llama3 license.

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