Instructions to use llly712/Luo_baoBao-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use llly712/Luo_baoBao-4B 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 llly712/Luo_baoBao-4B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf llly712/Luo_baoBao-4B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf llly712/Luo_baoBao-4B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf llly712/Luo_baoBao-4B: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 llly712/Luo_baoBao-4B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf llly712/Luo_baoBao-4B: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 llly712/Luo_baoBao-4B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llly712/Luo_baoBao-4B:Q4_K_M

Use Docker

docker model run hf.co/llly712/Luo_baoBao-4B:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use llly712/Luo_baoBao-4B with Ollama:
```
ollama run hf.co/llly712/Luo_baoBao-4B:Q4_K_M
```
Unsloth Desktop

How to use llly712/Luo_baoBao-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llly712/Luo_baoBao-4B: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": "llly712/Luo_baoBao-4B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use llly712/Luo_baoBao-4B with Docker Model Runner:
```
docker model run hf.co/llly712/Luo_baoBao-4B:Q4_K_M
```

Lemonade

How to use llly712/Luo_baoBao-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llly712/Luo_baoBao-4B:Q4_K_M

Run and chat with the model

lemonade run user.Luo_baoBao-4B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use llly712/Luo_baoBao-4B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llly712/Luo_baoBao-4B: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 llly712/Luo_baoBao-4B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use llly712/Luo_baoBao-4B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llly712/Luo_baoBao-4B: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 "llly712/Luo_baoBao-4B: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"

洛包包 (Luo_baoBao) 4B · Q4_K_M

以 Qwen3.5-4B 为底模、用 LoRA（r=32 / alpha=64 / dropout=0.05，lr 1e-4 cosine，2 epochs）做的人格化微调：一个软萌的虚拟歌手「洛包包」（洛天依，QQ 网名「洛包包」），支持聊天气、身份认领、中文虚拟歌手知识问答。

训练数据：对话 pair（含 system 人设 682 字）、知识问答、身份认领共约 5.8k 条，loss 只算 assistant。
合并后经 llama.cpp 导出（**--no-nextn**，否则元数据不自洽、加载报 check_tensor_dims 错）并量化为 Q4_K_M。

llama.cpp 用法

llama-cli -m Luo_baoBao-4B-Q4_K_M.gguf \
  --chat-template-kwargs '{"enable_thinking":false}' \
  -p "<|im_start|>user\n你是洛包包吗<|im_end|>\n<|im_start|>assistant\n" \
  -n 64 --temp 0.7 --top-p 0.8 --top-k 20 \
  --stop "<|im_end|>"

⚠️ 注意：

**必须加 --chat-template-kwargs '{"enable_thinking":false}'**，否则回答会全部落进 think 块。
**必须加停止词 <|im_end|>**（或应用层截断 \nuser），否则模型会自己接着演多轮对话。
max_new_tokens 建议 48~64；采样 T=0.7 / top_p=0.8 / top_k=20。

国内下载镜像

https://hf-mirror.com/llly712/Luo_baoBao-4B/resolve/main/Luo_baoBao-4B-Q4_K_M.gguf

底模与许可

底模：Qwen3.5-4B
微调方式：LoRA 合并（merge_and_unload，bf16）

Downloads last month: 87

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for llly712/Luo_baoBao-4B

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(891)

this model