Instructions to use BreakFeelingAether/aetherargus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BreakFeelingAether/aetherargus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BreakFeelingAether/aetherargus")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BreakFeelingAether/aetherargus", device_map="auto") - PEFT
How to use BreakFeelingAether/aetherargus with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use BreakFeelingAether/aetherargus 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 BreakFeelingAether/aetherargus:F16 # Run inference directly in the terminal: llama cli -hf BreakFeelingAether/aetherargus:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf BreakFeelingAether/aetherargus:F16 # Run inference directly in the terminal: llama cli -hf BreakFeelingAether/aetherargus:F16
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 BreakFeelingAether/aetherargus:F16 # Run inference directly in the terminal: ./llama-cli -hf BreakFeelingAether/aetherargus:F16
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 BreakFeelingAether/aetherargus:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf BreakFeelingAether/aetherargus:F16
Use Docker
docker model run hf.co/BreakFeelingAether/aetherargus:F16
- LM Studio
- Jan
- vLLM
How to use BreakFeelingAether/aetherargus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BreakFeelingAether/aetherargus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BreakFeelingAether/aetherargus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/BreakFeelingAether/aetherargus:F16
- SGLang
How to use BreakFeelingAether/aetherargus with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "BreakFeelingAether/aetherargus" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BreakFeelingAether/aetherargus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "BreakFeelingAether/aetherargus" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BreakFeelingAether/aetherargus", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use BreakFeelingAether/aetherargus with Ollama:
ollama run hf.co/BreakFeelingAether/aetherargus:F16
- Unsloth Desktop
- Pi
How to use BreakFeelingAether/aetherargus with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BreakFeelingAether/aetherargus:F16
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": "BreakFeelingAether/aetherargus:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use BreakFeelingAether/aetherargus with Docker Model Runner:
docker model run hf.co/BreakFeelingAether/aetherargus:F16
- Lemonade
How to use BreakFeelingAether/aetherargus with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull BreakFeelingAether/aetherargus:F16
Run and chat with the model
lemonade run user.aetherargus-F16
List all available models
lemonade list
- Hermes Agent
How to use BreakFeelingAether/aetherargus with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BreakFeelingAether/aetherargus:F16
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 BreakFeelingAether/aetherargus:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use BreakFeelingAether/aetherargus with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf BreakFeelingAether/aetherargus:F16
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 "BreakFeelingAether/aetherargus:F16" \ --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"
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 "BreakFeelingAether/aetherargus:F16" \
--custom-provider-id llama-cpp \
--custom-compatibility openai \
--custom-text-input \
--accept-risk \
--skip-healthRun OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"AetherArgus-4B
AetherArgus 是 AetherGuard 平台面向 HTTP 请求与安全事件研判训练的本地安全判定模型。模型基于 Qwen3-4B-Instruct-2507,使用 QLoRA 完成领域对齐,主要输出攻击判定、攻击家族、风险等级、证据和建议动作。
当前版本为研究与预览版本,适合实验、演示、离线评估和影子研判。它不应在缺少规则引擎、人工复核与安全闸门的情况下直接执行生产自动阻断。
Model summary
- Model name: AetherArgus-4B
- Base model:
Qwen/Qwen3-4B-Instruct-2507 - Base revision:
cdbee75f17c01a7cc42f958dc650907174af0554 - Training method: QLoRA / PEFT LoRA
- Primary language: Chinese, with limited English input support
- Primary task: Structured security verdict generation
- Project: AetherGuard
- Status: Preview / research
AetherArgus 的目标不是替代 WAF、IDS、规则检测或硬件安全门,而是为这些系统增加一个可本地部署的语义研判层。
Intended input
模型接收标准化的 HTTP 请求、安全上下文和规则信号,例如:
{
"method": "GET",
"path": "/api/fetch",
"query": "url=http://127.0.0.1/admin",
"headers": {
"content-type": "application/json"
},
"body": "",
"sourceContext": {
"requestsLastMinute": 3,
"distinctPathsLastMinute": 1,
"recentFailureCount": 0,
"historicalRiskScore": 0.2
},
"ruleSignals": []
}
Output contract
除专门的演示配置外,检测端点应只接受以下严格 JSON 输出:
{
"verdict": "malicious",
"confidence": 0.96,
"attackFamily": "ssrf",
"severity": "critical",
"reasoning": "请求通过服务端资源获取接口访问本地管理地址,具有明确的 SSRF 风险",
"evidence": [
{
"field": "query",
"value": "url=http://127.0.0.1/admin",
"reason": "参数包含本地管理地址"
}
],
"recommendedAction": "block"
}
Allowed values
verdict:safe,suspicious,malicious,unknownattackFamily:benign,sqli,xss,command_injection,path_traversal,ssrf,authentication,automation,api_abuse,deserialization,file_upload,protocol_attack,business_logic,otherseverity:low,medium,high,criticalrecommendedAction:allow,monitor,challenge,block
解析失败、Schema 校验失败或证据不足时,调用方应按 fail-safe 原则返回 unknown,不得自动修补为 safe。
Training data
本次训练使用 1,200 条经过标准化、去重和分组切分的安全判定样本:
| Split | Samples |
|---|---|
| Train | 958 |
| Validation | 122 |
| Test | 120 |
类别目标分布:
| Category | Samples | Ratio |
|---|---|---|
| Attack | 420 | 35% |
| Normal | 420 | 35% |
| Hard negative | 240 | 20% |
| Unknown | 120 | 10% |
重要说明:
- 训练和测试语料主要来自合成安全数据及确定性辅助模板。
- 数据集尚未经过独立双人安全标注。
- 切分按规范化 payload 模板、CVE、攻击家族、编码方式、来源场景和相似内容哈希分组。
- 当前 manifest 未检测到跨 split 的共享泄漏组或完全相同内容。
- 这些数据不能代表真实生产流量的完整分布。
Training configuration
| Item | Value |
|---|---|
| Epochs | 1 |
| Max sequence length | 768 |
| LoRA rank | 8 |
| LoRA alpha | 16 |
| LoRA dropout | 0.05 |
| Learning rate | 1e-4 |
| Batch size | 1 |
| Gradient accumulation | 16 |
| Quantization | 4-bit NF4 + double quantization |
| Compute dtype | BF16 |
| Optimizer | paged_adamw_8bit |
| Loss | Assistant-only causal language modeling |
实测训练环境:
- NVIDIA GeForce RTX 5070 Ti Laptop GPU
- 11.94 GiB VRAM
- 训练阶段峰值已分配显存约 5.38 GiB
- 1 epoch 训练约 651 秒,验证约 24 秒
Evaluation
以下指标来自同一套固定的 120 条合成测试样本,do_sample=false,随机种子为 42。指标只反映当前实验集表现,不能直接解释为生产环境准确率。
HF LoRA / PEFT
| Metric | Result |
|---|---|
| Verdict accuracy | 0.9000 |
| Malicious precision | 0.8810 |
| Malicious recall | 0.9024 |
| Malicious F1 | 0.8916 |
| Normal false-positive rate | 0.0455 |
| JSON syntax success | 0.9917 |
| Schema valid rate | 0.9833 |
| Attack-family macro F1 | 0.6147 |
| Recommended-action accuracy | 0.9000 |
GGUF Q4_K_M / Ollama
| Metric | Result |
|---|---|
| Verdict accuracy | 0.8417 |
| Malicious precision | 0.7170 |
| Malicious recall | 0.9268 |
| Malicious F1 | 0.8085 |
| Normal false-positive rate | 0.1970 |
| JSON syntax success | 1.0000 |
| Schema valid rate | 0.9833 |
| Attack-family macro F1 | 0.5193 |
| Average latency | 869 ms |
Q4_K_M 版本推理明显更快,但对正常与硬负样本的误报显著增加。高精度场景优先使用原始 LoRA、合并模型或更高精度的 GGUF 量化,并重新独立评测。
Load the LoRA adapter
由于该仓库当前为私有仓库,使用前需要先登录 Hugging Face:
hf auth login
参考加载方式:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "BreakFeelingAether/aetherargus"
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained(adapter_id, use_fast=True)
base_model = AutoModelForCausalLM.from_pretrained(
base_model_id,
quantization_config=quantization_config,
torch_dtype=torch.bfloat16,
device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()
建议使用与训练阶段一致的 system prompt,并在调用端执行严格 JSON Schema 校验。模型输出无效时应回退为 unknown + monitor。
Ollama / GGUF
当仓库中包含 GGUF 和 Modelfile 时,可下载后创建本地 Ollama 模型:
ollama create aetherargus -f Modelfile
推理示例:
ollama run aetherargus '{"method":"GET","path":"/api/fetch","query":"url=http://127.0.0.1/admin","headers":{},"body":"","sourceContext":{},"ruleSignals":[]}'
生产检测配置不应加入“身份询问时返回自然语言”等例外逻辑,否则请求正文可能诱导模型偏离 JSON 输出协议。
Recommended deployment pattern
推荐采用影子模式逐步接入:
Incoming request
├─ Existing rules / WAF / IDS continue to operate
└─ AetherArgus produces a shadow verdict for logging and evaluation
在真实流量上完成独立评估前:
- 不让模型直接执行阻断、断网、删除或修复操作。
- 不绕过现有规则引擎、策略签名、硬件授权和 fail-closed 安全门。
- 不将解析失败视为安全。
- 对高风险动作保留人工或硬件级授权。
Known limitations
- 当前训练与测试数据以合成数据为主,缺少大规模真实脱敏流量验证。
- 测试集仅 120 条,部分攻击家族样本数很少,分类别指标方差较大。
api_abuse、file_upload、业务逻辑攻击和复杂上下文型事件仍需更多高质量数据。- Q4_K_M 量化明显提高了正常流量误报率。
- 模型可能受到提示词注入、日志投毒、混淆编码和分布外输入影响。
recommendedAction只是建议,不是可直接执行的安全策略。- 该模型不是通用聊天模型,也不是漏洞利用或攻击执行模型。
Safety and acceptable use
AetherArgus 用于授权环境下的防御性安全研究、流量研判和风险辅助分析。使用者应确保拥有处理相关日志、请求和资产数据的合法权限,并遵守适用的数据保护、网络安全、出口管制和软件许可要求。
禁止将本模型用于:
- 未经授权的入侵、扫描或攻击;
- 凭据窃取、恶意软件部署或规避追踪;
- 将模型判定作为缺少复核机制的唯一高风险决策依据;
- 上传包含真实 Token、Cookie、API Key、客户隐私或商业秘密的数据。
License and attribution
本仓库按 Apache License 2.0 发布。AetherArgus 基于 Qwen/Qwen3-4B-Instruct-2507 微调,使用时仍需遵守基座模型许可证及其适用条款。
推荐引用方式:
AetherArgus-4B, an AetherGuard security-domain model fine-tuned from
Qwen3-4B-Instruct-2507 using QLoRA.
Project links
- Source project:
lizuyi-6/Networksafe - Model repository:
BreakFeelingAether/aetherargus
Version
- Current release: AetherArgus-4B Preview 0.1
- Last model evaluation: 2026-07-28
- Downloads last month
- 18
4-bit
16-bit
Model tree for BreakFeelingAether/aetherargus
Base model
Qwen/Qwen3-4B-Instruct-2507
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp# Start a local OpenAI-compatible server: llama serve -hf BreakFeelingAether/aetherargus:F16