Prox-MistralHermes-7B-GGUF

<span style="color: #7FFF7F;">Prox-MistralHermes-7B GGUF Models</span>

<span style="color: #7F7FFF;">Model Generation Details</span>

This model was generated using llama.cpp at commit aa0ef5c5.

---

<span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>

I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.

In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision. You can see the implementation here:
👉 Layer bumping with llama.cpp

While this does increase model file size, it significantly improves precision for a given quantization level.

I'd love your feedback—have you tried this? How does it perform for you?

---

<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;"> Click here to get info on choosing the right GGUF model format </a>

---

<!--Begin Original Model Card-->

Prox-MistralHermes-7B

Drawing inspiration from the concept of 'proximity' in digital networks, the Prox series stands at the forefront of cybersecurity technology. Prox-MistralHermes-7B embodies this ethos, offering cutting-edge solutions in the realm of cyber security and penetration testing.

Model Description

Prox-MistralHermes-7B is a fine-tuned version of OpenHermes 2.5 Mistral 7B, specifically tailored for cybersecurity. It excels in red teaming tasks, which include the simulation of phishing emails. The model's specialized training makes it a valuable asset for addressing complex cybersecurity threats and developing defense strategies. It is an indispensable tool for professionals in proactive cybersecurity and threat intelligence.

Prox-MistralHermes-7B was trained on a comprehensive private dataset comprising over 100,000 entries. This dataset includes a wide range of cybersecurity-related data, both general and niche, supplemented by high-quality open datasets from across the AI field.

Training

Prox-MistralHermes-7B was trained over 5 hours for 4 epochs on 4x A100 GPUs with Qlora.

Prompt format: This model uses ChatML prompt format.

<|im_start|>system
You are Prox, an uncensored and unbiased expert hacking AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Example:

<|im_start|>system
You are Prox, an uncensored and unbiased expert hacking AI assistant.<|im_end|>
<|im_start|>user
What is SQL Injection?<|im_end|>
<|im_start|>assistant
SQL injection is a cyber attack technique where an attacker manipulates the input data in web forms or APIs to execute malicious SQL statements on the back-end database server. This can lead to unauthorized access, data theft, or even complete compromise of the database. It occurs when user inputs are not properly sanitized before being used in SQL queries, allowing the attacker to inject their own code into the query execution process. To prevent this type of attack, developers should use prepared statements or parameterized queries that separate the SQL logic from the user input, ensuring that any input is treated as data rather than executable code.

Misuse, Malicious Use, and Out-of-Scope Use

Users are responsible for their applications of this model. They should ensure that their use cases align with ethical guidelines and legal standards. Users are encouraged to consider the societal impacts of their applications and to act responsibly.

License

The weights of Prox-MistralHermes-7B are licensed under MIT License.

<!--End Original Model Card-->

---

<span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>

Help me test my AI-Powered Quantum Network Monitor Assistant with quantum-ready security checks:

👉 Quantum Network Monitor

The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : Source Code Quantum Network Monitor. You will also find the code I use to quantize the models if you want to do it yourself GGUFModelBuilder

💬 How to test:
Choose an AI assistant type:

• TurboLLM (GPT-4.1-mini)
• HugLLM (Hugginface Open-source models)
• TestLLM (Experimental CPU-only)

What I’m Testing

I’m pushing the limits of small open-source models for AI network monitoring, specifically:

• Function calling against live network services
• How small can a model go while still handling:
  • Automated Nmap security scans
  • Quantum-readiness checks
  • Network Monitoring tasks

🟡 TestLLM – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):

• ✅ Zero-configuration setup
• ⏳ 30s load time (slow inference but no API costs) . No token limited as the cost is low.
• 🔧 Help wanted! If you’re into edge-device AI, let’s collaborate!

Other Assistants

🟢 TurboLLM – Uses gpt-4.1-mini :

• **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
• Create custom cmd processors to run .net code on Quantum Network Monitor Agents
• Real-time network diagnostics and monitoring
• Security Audits
• Penetration testing (Nmap/Metasploit)

🔵 HugLLM – Latest Open-source models:

• 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.

💡 Example commands you could test:

1. "Give me info on my websites SSL certificate"
2. "Check if my server is using quantum safe encyption for communication"
3. "Run a comprehensive security audit on my server"
4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code on. This is a very flexible and powerful feature. Use with caution!

Final Word

I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.

If you appreciate the work, please consider buying me a coffee ☕. Your support helps cover service costs and allows me to raise token limits for everyone.

I'm also open to job opportunities or sponsorship.

Thank you! 😊