Instructions to use SpaceSpider/dadong_model_8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SpaceSpider/dadong_model_8B with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SpaceSpider/dadong_model_8B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SpaceSpider/dadong_model_8B 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 SpaceSpider/dadong_model_8B:Q8_0
# Run inference directly in the terminal:
llama cli -hf SpaceSpider/dadong_model_8B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SpaceSpider/dadong_model_8B:Q8_0
# Run inference directly in the terminal:
llama cli -hf SpaceSpider/dadong_model_8B:Q8_0

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 SpaceSpider/dadong_model_8B:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf SpaceSpider/dadong_model_8B:Q8_0

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 SpaceSpider/dadong_model_8B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SpaceSpider/dadong_model_8B:Q8_0

Use Docker

docker model run hf.co/SpaceSpider/dadong_model_8B:Q8_0

LM Studio
Jan
Ollama
How to use SpaceSpider/dadong_model_8B with Ollama:
```
ollama run hf.co/SpaceSpider/dadong_model_8B:Q8_0
```
Unsloth Desktop

How to use SpaceSpider/dadong_model_8B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SpaceSpider/dadong_model_8B:Q8_0

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": "SpaceSpider/dadong_model_8B:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SpaceSpider/dadong_model_8B with Docker Model Runner:
```
docker model run hf.co/SpaceSpider/dadong_model_8B:Q8_0
```

Lemonade

How to use SpaceSpider/dadong_model_8B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SpaceSpider/dadong_model_8B:Q8_0

Run and chat with the model

lemonade run user.dadong_model_8B-Q8_0

List all available models

lemonade list

Hermes Agent

How to use SpaceSpider/dadong_model_8B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SpaceSpider/dadong_model_8B:Q8_0

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 SpaceSpider/dadong_model_8B:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SpaceSpider/dadong_model_8B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SpaceSpider/dadong_model_8B:Q8_0

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 "SpaceSpider/dadong_model_8B:Q8_0" \
  --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"

DaDong-Style Cybersecurity Article Generator

Model Description

This model is a specialized tool for generating popular science content in the field of cybersecurity, designed to write articles in the distinct style of the "Da Donghua Security" series. Through targeted training and optimization, the model can produce cybersecurity knowledge that is both highly professional and logically clear, while remaining accessible and easy to understand, thereby helping readers quickly grasp complex technical concepts and industry trends.

Key Features

🔍 Domain Expertise
Generates content covering essential cybersecurity topics including:

Security incident analysis
Attack/defense mechanisms
Security operation best practices
Emerging threat landscape

🎯 Instructional Design

Transforms complex security concepts into digestible explanations
Maintains technical accuracy while ensuring readability
Structures content with logical flow: background → analysis → enlightenment

✍️ Style Adaptation

Native support for "DaDong-style" narrative characteristics:
- Conversational teaching methodology
- Scenario-based learning approach
- Practical defense recommendations

Usage Scenarios

Cybersecurity awareness content creation
Technical blog/article generation

Quick Start

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("SpaceSpider/dadong_model_8B")
tokenizer = AutoTokenizer.from_pretrained("SpaceSpider/dadong_model_8B")

prompt = """
根据下面的文章主题，文章格式和文章风格撰写一篇文章
文章主题：xxx

文章格式：
大东话安全-热点事件篇模板

一、小白剧场
一个小场景引出热点事件

二、话说事件
该热点事件简要分析/概述

三、大话始末
该热点事件的影响/相关组织的反应

四、小白内心说
该热点事件所引发/内含的网安知识简要阐述（解决办法/预防措施）

五、参考资料（通常不少于3篇）
标注所参考文章题目

文章风格：以“大东”和“小白”两个人的幽默风趣的对话形式。
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=500)
print(tokenizer.decode(outputs[0]))

Downloads last month: 23

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for SpaceSpider/dadong_model_8B

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Quantized

unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit

Quantized

(49)

this model