Instructions to use liuc12712/MiniQCE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use liuc12712/MiniQCE 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 liuc12712/MiniQCE:Q4_K_M # Run inference directly in the terminal: llama cli -hf liuc12712/MiniQCE:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf liuc12712/MiniQCE:Q4_K_M # Run inference directly in the terminal: llama cli -hf liuc12712/MiniQCE:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf liuc12712/MiniQCE:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf liuc12712/MiniQCE:Q4_K_M
Use Docker
docker model run hf.co/liuc12712/MiniQCE:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use liuc12712/MiniQCE with Ollama:
ollama run hf.co/liuc12712/MiniQCE:Q4_K_M
- Unsloth Desktop
- Pi
How to use liuc12712/MiniQCE with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf liuc12712/MiniQCE: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "liuc12712/MiniQCE:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use liuc12712/MiniQCE with Docker Model Runner:
docker model run hf.co/liuc12712/MiniQCE:Q4_K_M
- Lemonade
How to use liuc12712/MiniQCE with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull liuc12712/MiniQCE:Q4_K_M
Run and chat with the model
lemonade run user.MiniQCE-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use liuc12712/MiniQCE with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf liuc12712/MiniQCE: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://127.0.0.1:9931/v1 hermes config set model.default liuc12712/MiniQCE:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use liuc12712/MiniQCE with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf liuc12712/MiniQCE: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://127.0.0.1:9931/v1 \ --custom-model-id "liuc12712/MiniQCE: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"
MiniQCE 模型
感谢您访问 MiniQCE 模型仓库!
MiniQCE 是一个轻量化的中文大语言模型,适合在本地通过 Ollama 调用进行实验与交互。
模型概览
- 模型名称:MiniQCE
- 模型类型:语言模型(LLM)
- 基于:Qwen2.5-1.5B模型178条数据QLoRA训练后合并量化
- 硬件配置:本地CPU即可,实测E3-1270V6处理器8秒内可完成150字左右的推理
- 训练目标:小型中文问答与对话实验
- 文件说明:
Modelfile:用于 Ollama 创建模型实例的配置文件- 模型权重文件:MiniQCE 模型文件(.gguf 格式)
使用要求
- Python >= 3.10
- Ollama 已安装
- 建议本地环境:可以结合 MiniQCE-Web-Demo GitHub 仓库 使用
快速使用
1️⃣ 安装 Ollama
请先安装 Ollama,用于本地管理 LLM 模型:
- 访问 Ollama 官方网站下载安装对应系统版本
- 安装完成后可通过命令检查版本:
ollama --version
2️⃣ 下载模型
在 Hugging Face 页面点击 "Download" 或使用 git-lfs / huggingface-cli 下载模型文件与 Modelfile。
3️⃣ 创建 Ollama 模型实例
在包含 Modelfile 的目录下执行:
ollama create miniqce -f Modelfile
执行完成后即可在本地通过 Ollama 调用 MiniQCE 模型。
4️⃣ 示例调用
import ollama
response = ollama.chat(
model="miniqce",
messages=[
{"role": "user", "content": "你好!"},
],
)
print(response['message']['content'])
说明与建议
- 模型为轻量化实验版本,适合本地研究与开发使用
- 如果结合 MiniQCE-Web-Demo GitHub 仓库 使用,可直接通过 Web 前端交互
- 后续会提供更多示例和教程
致谢
特别感谢 wttandroid 提供的前端模板,供 MiniQCE-Web-Demo 项目使用。 感谢 Hugging Face 社区提供的开源平台支持。
---
✅ **特点和建议**:
1. **结构清晰**:概览 → 环境 → 使用 → 示例 → 说明 → 致谢
2. **快速上手**:只要复制命令就能创建 Ollama 模型实例
3. **占位留空**:GitHub 链接和下载链接你可以后续补
4. **适合开源实验模型**:没有商业化约束,方便别人直接测试
- Downloads last month
- 1
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support