Instructions to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zzoceanpie/Qwen3-1.7B-Yukari-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zzoceanpie/Qwen3-1.7B-Yukari-DPO")
model = AutoModelForCausalLM.from_pretrained("zzoceanpie/Qwen3-1.7B-Yukari-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zzoceanpie/Qwen3-1.7B-Yukari-DPO",
	filename="Qwen3-1.7B-Yukari-DPO-f16.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16
# Run inference directly in the terminal:
llama-cli -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16
# Run inference directly in the terminal:
llama-cli -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO: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 zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16
# Run inference directly in the terminal:
./llama-cli -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO: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 zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16

Use Docker

docker model run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16

LM Studio
Jan

vLLM

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zzoceanpie/Qwen3-1.7B-Yukari-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zzoceanpie/Qwen3-1.7B-Yukari-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16

SGLang

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zzoceanpie/Qwen3-1.7B-Yukari-DPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zzoceanpie/Qwen3-1.7B-Yukari-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zzoceanpie/Qwen3-1.7B-Yukari-DPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zzoceanpie/Qwen3-1.7B-Yukari-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with Ollama:
```
ollama run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16
```

Unsloth Studio new

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO 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 zzoceanpie/Qwen3-1.7B-Yukari-DPO 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 zzoceanpie/Qwen3-1.7B-Yukari-DPO to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zzoceanpie/Qwen3-1.7B-Yukari-DPO to start chatting

Pi new

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO: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": "zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf zzoceanpie/Qwen3-1.7B-Yukari-DPO: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 zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16

Run Hermes

hermes

Docker Model Runner
How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with Docker Model Runner:
```
docker model run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16
```

Lemonade

How to use zzoceanpie/Qwen3-1.7B-Yukari-DPO with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zzoceanpie/Qwen3-1.7B-Yukari-DPO:F16

Run and chat with the model

lemonade run user.Qwen3-1.7B-Yukari-DPO-F16

List all available models

lemonade list

Qwen3-1.7B-Yukari-DPO

八云紫 (Yukari Yakumo) 角色扮演模型 — DPO 偏好对齐版。

在 SFT-v2 基础上用 DPO (Direct Preference Optimization) 做偏好对齐，消除攻击性输出、减少冗长偏好、降低公式化生成。

模型信息

项目	值
基座	Qwen/Qwen3-1.7B
起点	Qwen3-1.7B-Yukari-SFT-v2 (r=32, a=64)
方法	QLoRA 4-bit NF4 + DPO (sigmoid loss)
LoRA	r=32, alpha=64, target: q/k/v/o/gate/up/down proj
训练	3 epochs, beta=0.1, lr=1e-6, seed=42
DPO Loss	0.693 to 0.658
DPO Margin	+0.072
DPO Acc	87.5%
格式	Merged bf16 safetensors + GGUF F16

系列模型

模型	LoRA	方法	版本
Qwen3-1.7B-Yukari-SFT	r=8, a=8	SFT	v1
Qwen3-1.7B-Yukari-SFT-v2	r=32, a=64	SFT	v2
Qwen3-1.7B-Yukari-DPO (本模型)	r=32, a=64	SFT+DPO	v2+DPO

用法

模型输入格式为 [情绪标签]\n用户输入，标签控制八云紫的回复语气。8 维 Plutchik 情绪向量离散化：喜悦/愤怒/悲伤/恐惧/厌恶/惊讶/信任/期待，每维取「无」「极轻微」「轻微」「中轻度」「中度」「较强烈」「强烈」「极强烈」。

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "zzoceanpie/Qwen3-1.7B-Yukari-DPO",
    torch_dtype="auto", device_map="auto", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("zzoceanpie/Qwen3-1.7B-Yukari-DPO")

tags = "[<|中度喜悦|><|轻微愤怒|><|轻微悲伤|><|无恐惧|><|无厌恶|><|无惊讶|><|轻微信任|><|中度期待|>]"
prompt = f"{tags}\n你觉得人类最有趣的地方是什么？"

messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.8)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

GGUF

from llama_cpp import Llama

model = Llama(model_path="Qwen3-1.7B-Yukari-SFT-f16.gguf", n_ctx=2048, n_gpu_layers=-1)
response = model.create_chat_completion(
    messages=[{"role": "user", "content": prompt}],
    max_tokens=200, temperature=0.8
)
print(response["choices"][0]["message"]["content"])

许可 / License

模型权重: Apache 2.0
角色「八云紫」版权: (C) 上海爱丽丝幻乐团 (Team Shanghai Alice) / ZUN
本模型是东方Project的二次创作/粉丝作品。遵循东方Project二次创作指南。
训练数据: yukari-synthetic (Apache 2.0)
This is a fan-made derivative work based on Touhou Project. Touhou Project is (C) Team Shanghai Alice / ZUN.

This model is a fan-made derivative work based on Touhou Project. Touhou Project is (C) Team Shanghai Alice / ZUN. Please refer to the official guidelines for Touhou fan content.