Text Generation
MLX
Safetensors
Chinese
English
qwen3_5
qwen3.5
cybersecurity
nsec
fine-tuned
apple-silicon
conversational
Instructions to use QianqianTech/custos-1.0-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use QianqianTech/custos-1.0-mlx with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("QianqianTech/custos-1.0-mlx") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use QianqianTech/custos-1.0-mlx with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "QianqianTech/custos-1.0-mlx"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "QianqianTech/custos-1.0-mlx" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use QianqianTech/custos-1.0-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "QianqianTech/custos-1.0-mlx"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "QianqianTech/custos-1.0-mlx" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QianqianTech/custos-1.0-mlx", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use QianqianTech/custos-1.0-mlx with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "QianqianTech/custos-1.0-mlx"
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 QianqianTech/custos-1.0-mlx
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use QianqianTech/custos-1.0-mlx with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "QianqianTech/custos-1.0-mlx"
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 "QianqianTech/custos-1.0-mlx" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
custos 1.0(MLX)
产品名 custos 1.0。英文名 Custos,中文名顾斯。口号:Custos, guardian of digital realm|顾斯,数字疆域守护者。
内部训练版本:Custos-nesc-v1.2.5。基座为 Qwen3.5-9B。本仓库为 Apple Silicon 上的 MLX 16bit 权重。
微调用途
本仓库是面向政企安全运营场景的网络安全垂域微调权重,在 Qwen3.5-9B 上继续训练,用于威胁研判、攻击溯源、漏洞分析、合规审计与安全应急处置辅助。
能力范围
- 日志与告警辅助研判
- 攻击链路与威胁线索梳理
- 漏洞解读与风险分析
- 合规自查与材料编写
- 应急处置建议与复盘
本仓库格式
MLX 16bit safetensors,供 mlx_lm 在 macOS Apple Silicon 上加载。
vLLM / Transformers BF16 见对应仓库:
- Hugging Face:https://huggingface.co/QianqianTech/custos-1.0
- ModelScope:https://modelscope.cn/models/QianqianTech/custos-1.0
加载示例
python -m mlx_lm.server --model QianqianTech/custos-1.0-mlx --host 127.0.0.1 --port 8001
或:
from mlx_lm import load, generate
model, tokenizer = load("QianqianTech/custos-1.0-mlx")
魔搭源将仓库名换成 QianqianTech/custos-1.0-mlx。
许可与边界
基座 Qwen3.5-9B 为 Apache-2.0,本仓库权重按 Apache-2.0 发布。本页不声明开发主体、商业版本政策或认证资质。模型用于辅助研判与材料编写,不替代实际扫描、处置或合规结论。
- Downloads last month
- 94
Hardware compatibility
Log In to add your hardware
Quantized