Instructions to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF",
	filename="Llama-3-ELYZA-JP-YUA-1_q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with Ollama:
```
ollama run hf.co/nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M
```

Unsloth Studio

How to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with Docker Model Runner:
```
docker model run hf.co/nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M
```

Lemonade

How to use nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3-ELYZA-JP-YUA-1-GGUF-Q4_K_M

List all available models

lemonade list

nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF

Model Description

nori-sdc/Llama-3-ELYZA-JP-YUA-1-instruct is a Japanese instruction-tuned merged model based on elyza/Llama-3-ELYZA-JP-8B.

This model was developed with the cooperation and data provision of Saika Gakusha, a university entrance consulting organization. It was designed to support university entrance consultation, exam-life support, study planning, learning methods, and textbook selection.

The model aims to provide a YUA AI-style friendly and polite Japanese assistant with natural Japanese dialogue and domain-focused support for entrance exam preparation.

Version: v1.0
Model type: q4_k_m.gguf
Base model: elyza/Llama-3-ELYZA-JP-8B Developer: Noriyuki Sakai / 酒井紀之 (nori-sdc)

Intended Uses

This model is intended for educational support use cases such as:

university entrance consultation
exam-life support
study planning
learning method guidance
textbook selection guidance
statement of purpose writing support

Intended Users

high school students
parents
cram school instructors

Key Features

Friendly and polite dialogue style inspired by YUA AI
Natural Japanese responses
Better specialization in university entrance exam support than the base model
Practical support for study-related consultation and planning

Training Data

The model was trained using Japanese-language data provided with the cooperation of Saika Gakusha.

Data Categories

The training data included:

Q&A pairs
consultation dialogues
examples of statements of purpose
guidance on points to be careful about in interviews
study planning materials

Data Language

Japanese only

Personal Information

According to the developer, the training data does not contain personal information.

Data Availability

The training data itself is not publicly released.

Training

This model was developed through instruction tuning and LoRA fine-tuning, and is released as a merged model.

Frameworks and Libraries

The training environment and script were based on the following main frameworks and libraries:

PyTorch
Hugging Face Transformers
Hugging Face Datasets
PEFT (LoRA)
BitsAndBytes configuration support

Environment

Training was conducted in an environment including:

NVIDIA GeForce RTX 5090
Windows Server 2025
WSL2 Ubuntu
Conda

Evaluation

The model was evaluated through an exhaustive evaluation process using all available Q&A training data.

In this evaluation workflow, the model generated answers for the full Q&A dataset, and the outputs were then evaluated and ranked by an LLM-based evaluation program prepared by the developer.

Observed Improvements

Compared with the base model, this model showed improved specialization in knowledge related to university entrance exam preparation.

Limitations

This remains an 8B-class model and therefore has inherent capacity limitations.
The tuning process was conducted in an RTX 5090-based environment, which also imposes practical limits.
The model reflects information available up to March 2026 and may not reflect later changes or developments.

Safety and Usage Notes

This model is intended for reference and advisory use only. Final decisions should always be made by a human.

This model should not be used as the sole basis for school selection or life decisions.

Not Recommended For

definitive medical judgments
definitive legal judgments
deterministic school or career decisions based on potentially incorrect information
discriminatory, harmful, or abusive use

Use by Minors

This model is expected to be used by minors, including high school students. Human review and adult or educator support are recommended when the model is used for important educational or life decisions.

Acknowledgements

Special thanks to Saika Gakusha / 才華學舎 for their cooperation and data provision in the development of this model.

This model is built upon elyza/Llama-3-ELYZA-JP-8B by ELYZA, Inc., which is in turn based on Meta Llama 3 by Meta Platforms, Inc. We gratefully acknowledge both teams for their contributions to the open LLM community.

Contact / Related Link

Developer: Noriyuki Sakai / 酒井紀之 (nori-sdc)

YouTube: https://www.youtube.com/channel/UCjLYssqhbwkrRSPBOyO_xLw

License Notice

This model is derived from the ELYZA / Llama 3 family base model.

This model is licensed under the Meta Llama 3 Community License. See the LICENSE, Notice, and USE_POLICY.md files in this repository for full terms.

Users must comply with the license and usage conditions of the upstream base model.

Downloads last month: 19

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nori-sdc/Llama-3-ELYZA-JP-YUA-1-GGUF

Base model

elyza/Llama-3-ELYZA-JP-8B

Quantized

(14)

this model