Instructions to use hell0ks/ja-ko-vn-7b-v1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hell0ks/ja-ko-vn-7b-v1-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hell0ks/ja-ko-vn-7b-v1-gguf",
	filename="model-F16.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use hell0ks/ja-ko-vn-7b-v1-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hell0ks/ja-ko-vn-7b-v1-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 hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hell0ks/ja-ko-vn-7b-v1-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 hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M

Use Docker

docker model run hf.co/hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use hell0ks/ja-ko-vn-7b-v1-gguf with Ollama:
```
ollama run hf.co/hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M
```

Unsloth Studio

How to use hell0ks/ja-ko-vn-7b-v1-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 hell0ks/ja-ko-vn-7b-v1-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 hell0ks/ja-ko-vn-7b-v1-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hell0ks/ja-ko-vn-7b-v1-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use hell0ks/ja-ko-vn-7b-v1-gguf with Docker Model Runner:
```
docker model run hf.co/hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M
```

Lemonade

How to use hell0ks/ja-ko-vn-7b-v1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hell0ks/ja-ko-vn-7b-v1-gguf:Q4_K_M

Run and chat with the model

lemonade run user.ja-ko-vn-7b-v1-gguf-Q4_K_M

List all available models

lemonade list

A newer version of this model is available: hell0ks/ja-ko-vn-12b-v2-gguf

ja-ko-vn-7b

This model translates short dialogue from Japanese visual novels or other games into Korean.

For more detail, see hell0ks/ja-ko-vn-7b-v1.

이 모델은 일본어로 된 비주얼 노벨 혹은 타 게임의 짧은 대사를 한국어로 번역합니다.

상세 정보는 hell0ks/ja-ko-vn-7b-v1를 참고하세요.

Updates

2025/12/06 - Quant upload
2025/12/06 - 양자화 업로드
2025/12/07 - Fixed chat template
2025/12/07 - 채팅 템플릿을 수정했습니다

Model Details

Model Description

TrillionLabs의 Tri-7B-Base를 베이스로 해서, 그 위에 Visual Novel의 대사 원문(일본어)과 번역(한국어)을 SFT 한 모델입니다.

Developed by: hell0ks
Model type: Translation
Language(s) (NLP): Japanese(Input), Korean(Output)
License: Apache 2.0
Finetuned from model : trillionlabs/Tri-7B-Base
Max context length : 4096

Model Sources

Repository: hell0ks/ja-ko-vn-7b-v1

Uses

Temperature: 0.1, Top_k = 0.9 추천드립니다.
고유 명사, 이름 등은 System prompt로 힌트를 주실 수 있습니다. 예: 岡部倫太郎=오카베 린타로,阿万音鈴羽=아마네 스즈하
프롬프트는 일본어 원문만 입력하세요. 제어 코드나 특수문자도 최대한 그대로 유지하도록 학습되었습니다.
Chat 모드로 사용하지 마시고, Completions 모드로 사용하세요. 싱글 턴으로만 학습되었습니다.
llama.cpp에서 사용하실 때 꼭 --jinja 플래그를 사용하세요.

Bias, Risks, and Limitations

일본어에서 한국어 번역만 지원합니다. 반대나 다른 언어는 지원하지 않습니다. (오작동 발생)
Safety RL이 되지 않은 모델입니다. 출력문의 내용 및 결과물에 대해선 책임지지 않습니다.
고유명사 기능이 불안정할 수 있습니다. 발생하는 예시를 피드백 주시면 도움이 됩니다!

Downloads last month: 63

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for hell0ks/ja-ko-vn-7b-v1-gguf

Base model

trillionlabs/Tri-7B-Base

Finetuned

hell0ks/ja-ko-vn-7b-v1

Quantized

(1)

this model

Collection including hell0ks/ja-ko-vn-7b-v1-gguf

Ja-Ko-VN Translator

Collection

Specialized models for translating Japanese visual novels to Korean. • 4 items • Updated Dec 13, 2025