Yukari-Yakumo-Roleplay
Collection
Yukari Yakumo roleplay model • 4 items • Updated
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16 # Run inference directly in the terminal: llama cli -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16 # Run inference directly in the terminal: llama cli -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
# 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-GGUF:F16 # Run inference directly in the terminal: ./llama-cli -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
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-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
docker model run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with Ollama:
ollama run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with Pi:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
# 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": "zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16"
}
]
}
}
}# Start Pi in your project directory: pi
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with Docker Model Runner:
docker model run hf.co/zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
lemonade run user.Qwen3-1.7B-Yukari-GGUF-F16
lemonade list
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with Hermes Agent:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
# 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-GGUF:F16
hermes
How to use zzoceanpie/Qwen3-1.7B-Yukari-GGUF with OpenClaw:
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16
# 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 "zzoceanpie/Qwen3-1.7B-Yukari-GGUF:F16" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
openclaw agent --local --agent main --message "Hello from Hugging Face"
⚠️ 本仓库已归档,仅保留下载记录。请使用以下新仓库,三个版本均已内置 GGUF。
| 模型 | LoRA | 方法 | 仓库 |
|---|---|---|---|
| SFT (初版) | r=8, a=8 | SFT | Yukari-SFT |
| SFT (改进) | r=32, a=64 | SFT | Yukari-SFT-v2 |
| DPO (对齐) | r=32, a=64 | SFT+DPO | Yukari-DPO |
from llama_cpp import Llama
model = Llama(model_path="qwen3-1.7b-yukari-f16.gguf", n_ctx=2048, n_gpu_layers=-1)
# 情绪标签控制语气,8 维 Plutchik 离散化标签
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?"
response = model.create_chat_completion(
messages=[{"role": "user", "content": prompt}],
max_tokens=200, temperature=0.8
)
print(response["choices"][0]["message"]["content"])
16-bit