Instructions to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SakuraLLM/Sakura-GalTransl-14B-v3.8",
	filename="Sakura-Galtransl-14B-v3-IQ4_XS.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SakuraLLM/Sakura-GalTransl-14B-v3.8: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 SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SakuraLLM/Sakura-GalTransl-14B-v3.8: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 SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

Use Docker

docker model run hf.co/SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

LM Studio
Jan
Ollama
How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with Ollama:
```
ollama run hf.co/SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M
```

Unsloth Studio new

How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 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 SakuraLLM/Sakura-GalTransl-14B-v3.8 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 SakuraLLM/Sakura-GalTransl-14B-v3.8 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SakuraLLM/Sakura-GalTransl-14B-v3.8 to start chatting

Pi new

How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with Docker Model Runner:
```
docker model run hf.co/SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M
```

Lemonade

How to use SakuraLLM/Sakura-GalTransl-14B-v3.8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SakuraLLM/Sakura-GalTransl-14B-v3.8:Q4_K_M

Run and chat with the model

lemonade run user.Sakura-GalTransl-14B-v3.8-Q4_K_M

List all available models

lemonade list

模型介绍

基于Sakura-14B-Qwen2.5-v1.0，是GalTransl-v3模型的14b版本

得益于更大的底模，GalTransl-14B整体质量好于GalTransl-7B

本地部署方式和prompt模板等可以参考Sakura-GalTransl-7B-v3

推荐温度0.3，top_p 0.8

更新日志

2025.9 v3.8：改进文风，修正了部分已知的控制符号保留问题。注：不带后缀的版本量化等级为Q6_K
2025.7 v3.7：通过改进的强化学习，显著改进了整体质量并减少人称错误
2025.5 v3：初版

autodl部署教程

参考https://books.fishhawk.top/forum/65719bf16843e12bd3a4dc98 ，选择4090部署FishHawk/auto-novel/Sakura-LNovel v1.0.0版镜像

打开JupyterLab后，按顺序输入以下2个命令

下载模型：

wget https://hf-mirror.com/SakuraLLM/Sakura-GalTransl-14B-v3.8/resolve/main/Sakura-Galtransl-14B-v3.8.gguf

不要按教程运行.run，而是运行下面的命令：

./llama.cpp/llama-server -m Sakura-Galtransl-14B-v3.8.gguf -c 32768 -np 16 -fa -ngl 999 -a Sakura-Galtransl-14B-v3.8 --port 6006

然后继续按"SSH转发服务到本地"操作即可。接口地址为http://127.0.0.1:6006 ，翻译时可以设置16线程最大化速度，16线程跑满时每小时大约翻译3w句

Downloads last month: 8,732

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

View +1 variant

Inference Providers NEW

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

Model tree for SakuraLLM/Sakura-GalTransl-14B-v3.8

Quantizations

4 models