Instructions to use zephyrox29/iiio-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use zephyrox29/iiio-1.0 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 zephyrox29/iiio-1.0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zephyrox29/iiio-1.0:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zephyrox29/iiio-1.0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zephyrox29/iiio-1.0: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 zephyrox29/iiio-1.0:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zephyrox29/iiio-1.0: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 zephyrox29/iiio-1.0:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zephyrox29/iiio-1.0:Q4_K_M

Use Docker

docker model run hf.co/zephyrox29/iiio-1.0:Q4_K_M

LM Studio
Jan
Ollama
How to use zephyrox29/iiio-1.0 with Ollama:
```
ollama run hf.co/zephyrox29/iiio-1.0:Q4_K_M
```
Unsloth Desktop

How to use zephyrox29/iiio-1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zephyrox29/iiio-1.0: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": "zephyrox29/iiio-1.0:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use zephyrox29/iiio-1.0 with Docker Model Runner:
```
docker model run hf.co/zephyrox29/iiio-1.0:Q4_K_M
```

Lemonade

How to use zephyrox29/iiio-1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zephyrox29/iiio-1.0:Q4_K_M

Run and chat with the model

lemonade run user.iiio-1.0-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use zephyrox29/iiio-1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zephyrox29/iiio-1.0: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 zephyrox29/iiio-1.0:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use zephyrox29/iiio-1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zephyrox29/iiio-1.0: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 "zephyrox29/iiio-1.0: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"

Model Card for IIIO-1.0

IIIO-1.0 是由合肥第一中学电脑社团开发的开源中文对话大语言模型，以 GGUF 格式发布，支持本地推理（Ollama / llama.cpp / LM Studio）与在线体验。模型面向中文场景优化，可用于教育展示、学习辅助与日常对话。

Model Details

Model Description

IIIO-1.0 是一个约 7B 参数规模的中文对话模型，本次发布为 Q4_K_M 量化 版本（单文件约 4.68 GB），可在消费级硬件上运行。模型支持多轮对话，适合个人本地部署与教学演示。

Developed by: 合肥第一中学（Hefei No.1 High School）
Funded by [optional]: None
- Shared by [optional]: Xianfish(Zephyrox29)
Model type: 因果语言模型（Causal LM），量化版本为 GGUF (Q4_K_M)
Language(s) (NLP): 中文
License: CC-BY-NC-4.0（仅限非商业用途）
Finetuned from model [optional]: unsloth/Qwen2.5-7B-Instruct-bnb-4bit

Model Sources

Repository (Hugging Face): https://huggingface.co/zephyrox29/iiio-1.0

Uses

Direct Use

通过 Ollama 直接运行（Modelfile 中引用本仓库 GGUF 文件）
通过 llama.cpp / LM Studio / GPT4All 等支持 GGUF 的工具本地推理

Downstream Use [optional]

基于原始（未量化）权重进行进一步微调
作为智能体/应用的后端模型接入

Out-of-Scope Use

商业用途：许可协议为 CC-BY-NC-4.0，禁止商业使用
生成违法、有害或误导性内容
用于高风险决策（医疗诊断、法律裁决、金融决策等）而未经人工复核

Bias, Risks, and Limitations

Q4_K_M 为 4-bit 量化版本，与原始全精度权重相比存在一定的精度损失，复杂推理与长文本任务表现可能下降
模型可能生成不准确、有偏见或不恰当的内容，输出不应被视为事实或专业建议
上下文窗口有限（Demo 中设置为 4096），超出后早期对话内容会被截断
未做针对性的安全对齐评估，请勿在未审核的情况下将输出直接面向未成年人发布

Recommendations

使用者应了解模型的上述局限；面向公众（尤其是学生）部署时，建议添加内容过滤与人工监督机制。

How to Get Started with the Model

Ollama

Training Details

Training Data

手写、GPT 5.3合成、Python清洗

Training Procedure

Training Hyperparameters

Training regime: LoRA

Speeds, Sizes, Times [optional]

量化文件大小: 4.68 GB (Q4_K_M)

Technical Specifications

Model Architecture and Objective

约 7B 参数的 Transformer 因果语言模型；本仓库发布 Q4_K_M 量化权重，兼顾质量与显存/内存占用（运行时内存占用约 5 GB）。

Compute Infrastructure

Hardware

T4 GPU

Software

推理：llama.cpp / llama-cpp-python / Ollama（GGUF 生态）

Model Card Authors

李先羽（合肥第一中学）

Model Card Contact

hfyzdns.cn

Downloads last month: 26

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for zephyrox29/iiio-1.0

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

unsloth/Qwen2.5-7B-Instruct-bnb-4bit

Quantized

(23)

this model