Instructions to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Murasaki-Project/Murasaki-APE-Aligner-2B-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 Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Murasaki-Project/Murasaki-APE-Aligner-2B-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 Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Murasaki-Project/Murasaki-APE-Aligner-2B-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 Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Murasaki-Project/Murasaki-APE-Aligner-2B-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 Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

Ollama
How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with Ollama:
```
ollama run hf.co/Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M
```

Lemonade

How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Murasaki-APE-Aligner-2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF: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 Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Murasaki-APE-Aligner-2B-GGUF

Github | Murasaki Translator | License: MIT

Other Versions: Base (BF16) | AWQ (4-bit)

简介

Murasaki-APE-Aligner-2B 是基于 Qwen-3.5-2B 训练的轻量级格式修复模型，专为 ACGN 文本翻译（如含有大量控制代码的 Galgame、RPG 脚本等）的后处理与对齐任务设计。此仓库提供的是GGUF格式的量化版本

训练数据与核心能力：为了应对极其复杂的真实游戏文本环境，本模型使用了涵盖 40 种以上 Galgame 与 RPG 游戏引擎、超过 1000 种不同格式的游戏控制符数据进行针对性训练。模型能够处理绝大多数控制符错位、丢失、冗余或参数被错误翻译的问题，并稳定输出逻辑正确、语法及代码完全正确的文本。

核心机制：读取包含原文与模型初翻的 JSON 格式输入，自动对齐并修复草稿中损坏的控制代码。模型仅处理代码与格式规范，不会改动任何译文的具体内容。修复完成后直接输出纯文本字符串。

核心 Prompt 与输入输出格式

请使用以下格式激活模型的修复与对齐能力：

1. System Prompt

你是一个格式修复引擎。请读取JSON输入的原文和草稿，修复草稿中的控制符和格式，直接输出修复后的字符串，不要输出任何额外的JSON标签或解释。

2. User Input

必须为包含 ja (原文) 和 zh (译文初翻) 的 JSON 字符串：

{"ja": "その意思は[font color=0x64E560]尊重[resetfont]したいが……", "zh": "我很想[font color=0x64E560]尊重[resetfont][resetfont]你的意志……"}

3. Model Output

模型将直接返回修复后的纯文本，无任何多余的 JSON 嵌套或解释：

我很想[font color=0x64E560]尊重[resetfont]你的意志……

建议超参数 (Recommended Hyperparameters)

推荐参数如下：

temperature: 0.0 ~ 0.1 (越低越稳定)
top_p: 1.0
top_k: 1 (或禁用)
repetition_penalty: 1.0 ~ 1.05

Downloads last month: 62

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

6-bit

16-bit

Model tree for Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF

Base model

Murasaki-Project/Murasaki-APE-Aligner-2B

Quantized

(4)

this model

Collection including Murasaki-Project/Murasaki-APE-Aligner-2B-GGUF

Murasaki-APE-Aligner-2B

Collection

3 items • Updated Mar 11