--- tags: - autotrain - text-generation-inference - text-generation - cybersécurity - BLUE - EDGEAI - GRC library_name: transformers base_model: mistralai/Mistral-7B-Instruct-v0.3 widget: - messages: - role: user content: What is your favorite condiment? license: apache-2.0 language: - en - fr --- # ELISARCyberAIEdge7B > **Maintainer:** Dr. Sabri Sallani > **Expertise:** AI Research & Cybersecurity > **Adapter type:** LoRA (Low-Rank Adaptation) > **Base model:** mistralai/Mistral-7B-v0.1 (FP16) > **Intended use:** Offline edge deployment for CyberAI & Blue-Team scenarios > **License:** Apache 2.0 (see LICENSE) --- ## 📖 Overview **ELISARCyberAIEdge7B** is a LoRA adapter crafted by Dr. Sabri Sallani—AI & cybersecurity researcher—to specialize Mistral-7B for offline, on-device CyberAI and “Blue AI” (defensive) applications. Once merged with the FP16 base, you obtain a single \~5 GB GGUF that runs natively on edge hardware (e.g., Raspberry Pi 4, Jetson Nano, NVIDIA T4) without internet access.

ELISAR - AI for Cybersecurity

Key points: * 🔧 **LoRA-only:** Contains low-rank delta-weights for Mistral-7B. * 🛠️ **Edge-optimized:** Full merged GGUF runs entirely offline on typical edge GPUs/accelerators. * 🚀 **Cybersecurity focus:** Fine-tuned on “ELISAR CyberAI Edge” corpus—vulnerability descriptions, incident reports, secure-coding examples, threat intelligence summaries. * 👤 **Authored by Dr. Sabri Sallani:** Published under the ELISAR initiative. --- ## ⚙️ Installation 1. **Python dependencies** ```bash pip install transformers peft accelerate sentencepiece torch ``` 2. *(Optional)* **llama.cpp + GGUF tools** (to merge and run offline) ```bash # Clone and install gguf-py git clone --depth 1 https://github.com/ggml-org/llama.cpp.git pip install ./llama.cpp/gguf-py pip install llama-cpp-python ``` → Use these tools to merge LoRA + base weights into a single GGUF. --- ## 🐍 Usage ### 1. Inference with `transformers` + `PEFT` (online GPU/CPU) ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel BASE_ID = "mistralai/Mistral-7B-v0.1" ADAPTER_ID = "sallani/ELISARCyberAIEdge7B" # 1) Load Mistral-7B base (FP16 or BF16) with automatic device placement tokenizer = AutoTokenizer.from_pretrained(BASE_ID, use_fast=True) base_model = AutoModelForCausalLM.from_pretrained( BASE_ID, torch_dtype="auto", device_map="auto" ) # 2) Load LoRA adapter on top model = PeftModel.from_pretrained( base_model, ADAPTER_ID, torch_dtype="auto", device_map="auto" ) model.eval() # 3) Perform inference prompt = ( "### Instruction:\n" "Propose a set of secure-coding guidelines for Python web applications.\n" "### Response:\n" ) inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): out = model.generate( **inputs, max_new_tokens=128, temperature=0.8, top_p=0.9, repetition_penalty=1.1 ) print(tokenizer.decode(out[0], skip_special_tokens=True)) ``` * **device\_map="auto"** places weights on GPU/CPU automatically (FP16 when supported). * Adjust sampling parameters (`temperature`, `top_p`, `repetition_penalty`) for your use case. ### 2. Offline Edge Deployment via `llama.cpp` (Merged GGUF) 1. **Merge LoRA + base into a single GGUF** ```bash python3 llama.cpp/convert_lora_to_gguf.py \ sallani/ELISARCyberAIEdge7B \ # LoRA repo or local folder --base-model-id mistralai/Mistral-7B-v0.1 \ # HF ID of FP16 base --outfile elisar_full_f16.gguf # Output GGUF (~5 GB) ``` * The script pulls the FP16 base automatically from HF, applies LoRA deltas, and writes a merged GGUF. 2. **Run inference on edge** * Copy `elisar_full_f16.gguf` to your edge device (Jetson Nano, Raspberry Pi 4 + GPU, NVIDIA T4). * Use `llama.cpp` binary to run: ```bash ./llama.cpp/main \ -m elisar_full_f16.gguf \ -p "### Instruction: Audit the following log entries for suspicious activity.\n---\n\n---\n### Response:" \ --temp 0.7 \ --repeat_penalty 1.1 \ --n 128 ``` * **No internet** is required once the GGUF is on-device. --- ## 📐 Model Details * **Base architecture:** Mistral-7B-v0.1 (40 transformer layers, 4096-dim embedding, 32 heads, causal LM). * **LoRA configuration:** * Rank = 64, α = 16 * Applied to Q/K/V and feed-forward projections * Adapter snapshots ≈ 168 MB * **Training corpus (ELISAR CyberAI Edge):** * Public vulnerability databases (CVE entries, CVSS scoring). * Real-world incident reports (MITRE ATT\&CK red vs. blue logs). * Secure-coding patterns (OWASP Top 10, SAST examples). * Blue-team playbooks and defensive strategies. * **Hyperparameters:** * Learning rate = 1e-4, batch size = 16 per GPU, 3 epochs on 8×A100 (FP16). * Validation on unseen CVE descriptions and red-team prompts. * **Merged GGUF (FP16):** * \~5 GB total after merging and trimming unnecessary metadata for on-device use. --- ## 🔖 Prompt Guidelines * **Structured prompt** ``` ### Instruction: ### Response: ``` * **Recommended sampling** * `temperature=0.7–0.9` for balanced creativity. * `top_p=0.9` for nucleus sampling. * `repetition_penalty=1.1` to reduce loops. --- --- language: en license: apache-2.0 tags: - gguf - quantized - cybersecurity - edge-llm - lora - mistral - elisar model_name: ELISARCyberAIEdge7B-LoRA-GGUF pipeline_tag: text-generation datasets: - custom widget: - text: "What are the main threats targeting OT environments?" ## 📊 Stats & Adoption * 🔄 Download tracking: [Enabled](https://huggingface.co/sallani/ELISARCyberAIEdge7B) * 📥 Total downloads (last 30 days): _auto-updated by HF_ * 🧪 Being tested on: - Jetson Nano (Ubuntu 20.04, CUDA 11.4) - Raspberry Pi 4 (with Coral TPU) - NVIDIA T4 + LLaMA.cpp Want to share your benchmarks? Open an [Issue](https://huggingface.co/sallani/ELISARCyberAIEdge7B/issues) or pull request. ## ⚠️ License & Citation * **License:** Apache 2.0 (see [LICENSE](LICENSE)). * **Attribution:** > Sallani, S. (2025). *ELISARCyberAIEdge7B: LoRA adapter for Mistral-7B specializing in offline CyberAI Edge tasks*. Hugging Face Model Hub: `sallani/ELISARCyberAIEdge7B`. --- ## 🛠️ Support & Contact * **Report issues or feature requests:** [https://huggingface.co/sallani/ELISARCyberAIEdge7B/issues](https://huggingface.co/sallani/ELISARCyberAIEdge7B/issues) * **Contact the author:** Dr. Sabri Sallani • GitHub: [@sallani](https://github.com/sallani) • Email: `sabri.sallani@cyberaiedge.com` • LinkedIn: [linkedin.com/in/sabri-sallani](https://linkedin.com/in/sabri-sallani) Thank you for using **ELISARCyberAIEdge7B**. This adapter empowers secure, offline AI at the edge for next-gen CyberAI and Blue-Team applications.