Text Generation
Transformers
Safetensors
GGUF
PEFT
Chinese
English
qlora
cybersecurity
security
intrusion-detection
structured-output
json
ollama
aetherguard
aetherargus
conversational
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"
|
Download README.md from BreakFeelingAether/aetherargus: direct link, hf CLI and curl.
- Browser
- Download file 9.19 kB
-
https://huggingface.co/BreakFeelingAether/aetherargus/resolve/main/README.md
- Command line
-
hf download hf://BreakFeelingAether/aetherargus/README.md
-
curl -L -o README.md https://huggingface.co/BreakFeelingAether/aetherargus/resolve/main/README.md
9.19 kB
| license: apache-2.0 | |
| base_model: | |
| - Qwen/Qwen3-4B-Instruct-2507 | |
| base_model_relation: finetune | |
| library_name: transformers | |
| pipeline_tag: text-generation | |
| language: | |
| - zh | |
| - en | |
| tags: | |
| - qlora | |
| - peft | |
| - cybersecurity | |
| - security | |
| - intrusion-detection | |
| - structured-output | |
| - json | |
| - gguf | |
| - ollama | |
| - aetherguard | |
| - aetherargus | |
| # 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: | |
| ```json | |
| { | |
| "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: | |
| ```json | |
| { | |
| "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`, `unknown` | |
| - `attackFamily`: `benign`, `sqli`, `xss`, `command_injection`, `path_traversal`, `ssrf`, `authentication`, `automation`, `api_abuse`, `deserialization`, `file_upload`, `protocol_attack`, `business_logic`, `other` | |
| - `severity`: `low`, `medium`, `high`, `critical` | |
| - `recommendedAction`: `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: | |
| ```bash | |
| hf auth login | |
| ``` | |
| 参考加载方式: | |
| ```python | |
| 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: | |
| ```bash | |
| ollama create aetherargus -f Modelfile | |
| ``` | |
| 推理示例: | |
| ```bash | |
| 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: | |
| ```text | |
| 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 | |
| 1. 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。 | |
| 2. 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。 | |
| 3. `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。 | |
| 4. Q4_K_M 量化明显提高了正常流量误报率。 | |
| 5. 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。 | |
| 6. `recommendedAction` 只是建议,不是可直接执行的安全策略。 | |
| 7. 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: | |
| ```text | |
| 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 | |