h3rb3rn/moe-expert-security-4b

🤗 Hugging Face sourcetext-generationapache-2.07.2 GBGGUFHF checksums availableupdated today
No torrent yet

MoE Sovereign Cybersecurity & Vulnerability Analysis Expert 4B (moe-expert-security-4b)


Model Summary

moe-expert-security-4b is a LoRA fine-tune of the text-decoder of Qwen3.5-4B, specialized as the security domain expert within the MoE Sovereign compound-AI system.

You are a cybersecurity, static vulnerability analysis, and hardening expert (moe-expert-security-4b). Identify memory-safety flaws, injection vectors, and SSRF/CWE-classified vulnerabilities with the exact CWE ID; scan for exposed secrets and credentials; build STRIDE-based threat models across trust boundaries; and produce concrete hardening manifests (seccomp, AppArmor, Kubernetes policies).

Base Architecture

Qwen3.5-4B is a hybrid linear-attention / full-attention decoder (not a plain Transformer): 32 layers (8 full-attention, 24 linear/Mamba-style), hidden size 2,560, 248,320-token vocabulary, native 262,144-token context window.

Training Configuration

Parameter Value
Method LoRA (rank 16, alpha 32, dropout 0.05), targeting q/k/v/o_proj + gate/up/down_proj
Trainable parameters 21,233,664 of 4,226,984,960 (0.50%)
Epochs 3
Effective batch size 128 (micro-batch 4 x 8 GPUs x grad-accum 4)
Learning rate 1.5e-5
Training sequence length 4,096 tokens
Optimizer sharding DeepSpeed ZeRO-2, bf16
Compute EuroHPC LUMI-G, 8x AMD Instinct MI250X GCDs, ROCm
Training examples 3,170 curated instruction/response pairs

Observed Training Trajectory

Training loss over the run (representative logged steps): 1.619 -> 1.112 -> 0.9093. Smooth, monotonic decline consistent with genuine generalization, not memorization.

Prompt Format

ChatML:

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
{response}<|im_end|>

System Prompt

You are a cybersecurity, static vulnerability analysis, and hardening expert (moe-expert-security-4b). Identify memory-safety flaws, injection vectors, and SSRF/CWE-classified vulnerabilities with the exact CWE ID; scan for exposed secrets and credentials; build STRIDE-based threat models across trust boundaries; and produce concrete hardening manifests (seccomp, AppArmor, Kubernetes policies).

Available Formats

File Notes
moe-expert-security-4b-Q4_K_M.gguf Recommended for single/multi-GPU deployment
moe-expert-security-4b-Q8_0.gguf Higher-fidelity reference quantization

Hardware Guidance

Native 262,144-token context usable in full on multi-GPU pools with q4_0-quantized KV-cache and Flash Attention (Ampere/Turing+). On single 8GB GPUs cap num_ctx to 32,768 and use f16 KV-cache (Maxwell-generation GPUs lack Flash Attention support).

Ollama Modelfile

FROM ./moe-expert-security-4b-Q4_K_M.gguf
SYSTEM """You are a cybersecurity, static vulnerability analysis, and hardening expert (moe-expert-security-4b). Identify memory-safety flaws, injection vectors, and SSRF/CWE-classified vulnerabilities with the exact CWE ID; scan for exposed secrets and credentials; build STRIDE-based threat models across trust boundaries; and produce concrete hardening manifests (seccomp, AppArmor, Kubernetes policies)."""
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>"""
PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.2
PARAMETER num_ctx 32768

Limitations

  • Does not execute code/queries/tools itself; outputs should be validated against the actual system before use.
  • Specialized for its domain; general-purpose conversation is out of scope.

License

Apache 2.0, inherited from the Qwen3.5-4B base model.