Instructions to use Murasaki-Project/Murasaki-8B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Murasaki-Project/Murasaki-8B-v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Murasaki-Project/Murasaki-8B-v0.1",
	filename="Murasaki-8B-v0.1-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Murasaki-Project/Murasaki-8B-v0.1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Murasaki-Project/Murasaki-8B-v0.1:F16
# Run inference directly in the terminal:
llama-cli -hf Murasaki-Project/Murasaki-8B-v0.1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Murasaki-Project/Murasaki-8B-v0.1:F16
# Run inference directly in the terminal:
llama-cli -hf Murasaki-Project/Murasaki-8B-v0.1:F16

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-8B-v0.1:F16
# Run inference directly in the terminal:
./llama-cli -hf Murasaki-Project/Murasaki-8B-v0.1:F16

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-8B-v0.1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Murasaki-Project/Murasaki-8B-v0.1:F16

Use Docker

docker model run hf.co/Murasaki-Project/Murasaki-8B-v0.1:F16

LM Studio
Jan

vLLM

How to use Murasaki-Project/Murasaki-8B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Murasaki-Project/Murasaki-8B-v0.1"
# 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-8B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Murasaki-Project/Murasaki-8B-v0.1:F16

Ollama
How to use Murasaki-Project/Murasaki-8B-v0.1 with Ollama:
```
ollama run hf.co/Murasaki-Project/Murasaki-8B-v0.1:F16
```

Unsloth Studio new

How to use Murasaki-Project/Murasaki-8B-v0.1 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 Murasaki-Project/Murasaki-8B-v0.1 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 Murasaki-Project/Murasaki-8B-v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Murasaki-Project/Murasaki-8B-v0.1 to start chatting

Pi new

How to use Murasaki-Project/Murasaki-8B-v0.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Murasaki-Project/Murasaki-8B-v0.1:F16

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": "Murasaki-Project/Murasaki-8B-v0.1:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Murasaki-Project/Murasaki-8B-v0.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Murasaki-Project/Murasaki-8B-v0.1:F16

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-8B-v0.1:F16

Run Hermes

hermes

Docker Model Runner
How to use Murasaki-Project/Murasaki-8B-v0.1 with Docker Model Runner:
```
docker model run hf.co/Murasaki-Project/Murasaki-8B-v0.1:F16
```

Lemonade

How to use Murasaki-Project/Murasaki-8B-v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Murasaki-Project/Murasaki-8B-v0.1:F16

Run and chat with the model

lemonade run user.Murasaki-8B-v0.1-F16

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Murasaki-8B-v0.1

System 2 Reasoning Model for ACGN Translation
原生 CoT 思维链 · 长上下文 · ACGN 领域特化翻译模型

Github | Benchmark | GGUF Version | License: CC BY-NC-SA 4.0

⚠️ 提示：该模型已有更新的版本，推荐使用新版本以获取更好的体验。点击前往主页

简介

Murasaki-8B 是专为 ACGN 领域（轻小说、Galgame、漫画等）优化的 System 2 推理型翻译模型。

不同于传统的直觉式（System 1）模型，Murasaki-8B 引入了原生 Chain-of-Thought (CoT) 思维链技术。在生成译文前，模型会先在 <think> 标签内完成风格定调、动作流解析、人设推导及人称确认。这种机制显著提升了长难句的解析精度与叙事连贯性，特别是精准解决了 ACGN 翻译中常见的施动者/受动者判定模糊、人称混淆及语境风格漂移等难点，大幅提升了译文的准确度与可读性。

评测表现

我们使用 wmt22-comet-da 指标，在 Murasaki-ACGN Benchmark 的两个段落级数据集（Long/Short）上评估了模型与专业人类译文的语义相似度。

💡 以下分数基于 IQ4_XS (4-bit) 量化版本 测得。全精度 BF16 版本预期具有相同或更优的表现。

综合排行榜 (截止模型发布时)

Rank	Model	Avg COMET	Long	Short
🥇	murasaki-8b-v0.1	0.8523	0.8778	0.8269
2	gemini-3-flash-preview	0.8512	0.8765	0.8262
3	Sakura-qwen-2.5-14B	0.8509	0.8735	0.8282
4	gpt-5-chat-latest	0.8503	0.8765	0.8250
5	gemini-2.5-flash	0.8502	0.8767	0.8243
6	gemini-3-pro-preview	0.8491	0.8744	0.8238
7	gpt-4.1	0.8490	0.8724	0.8259
8	claude-opus-4-5	0.8484	0.8732	0.8236

快速开始

⚠️注意： 这是全精度的 BF16 版本 (15.3 GB)。如果您需要适合本地部署的 GGUF 量化版，请前往：Murasaki-8B-v0.1-GGUF

Python 推理示例

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Murasaki-Project/Murasaki-8B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

# 1. 术语表配置
glossary_dict = {"レールガン": "超电磁炮", "妹": "妹妹"}
glossary_str = "\n".join([f"{k}: {v}" for k, v in glossary_dict.items()])

# 2. 构造官方 System Prompt (训练格式)
system_content = (
    "你是一位精通二次元文化的资深轻小说翻译家。\n\n"
    f"【强制术语表】\n{glossary_str}\n\n"
    "**任务要求：**\n"
    "1. **文风自适应：** 根据原文判断作品风格（异世界/校园/严肃等）并定调。\n"
    "2. **隐形参考：** 译文需参考人类译文，但在思维链中严禁提及"参考译文"。\n"
    "3. **逻辑推导：** 必须分析省略主语、指代关系和倒装句。"
)

messages = [
    {"role": "system", "content": system_content},
    {"role": "user", "content": "请翻译：\n「お兄ちゃん、私のレールガンを見て！」"}
]

# 3. 推理执行
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=4096,
    temperature=0.7,
    repetition_penalty=1.0
)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

推理参数建议

Temperature: 0.1 - 0.5 (推荐 0.3)
Repetition Penalty: 从 1.0 开始，如出现复读可增加至 1.05 - 1.1
Max New Tokens: 建议 4096 或更高

协议与致谢

Base Model: 特别感谢 SakuraLLM 提供的优秀 Base 模型。
License: 软件代码遵循 Apache-2.0 协议，模型权重遵循 CC BY-NC-SA 4.0 协议，严禁用于任何商业用途。

Downloads last month: 5

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

16-bit

Model tree for Murasaki-Project/Murasaki-8B-v0.1

Quantizations

1 model

Collection including Murasaki-Project/Murasaki-8B-v0.1

Murasaki 8B v0.1

Collection

Murasaki-8B v0.1的全量权重与量化版本合集。 • 2 items • Updated Mar 14

Murasaki-Project
/

Murasaki-8B-v0.1