nyxspecter4/kin-cybersecurity-3b-gguf
0646
KIN Cybersecurity 3B — GGUF (Quantized)
Quantized GGUF version of KIN Cybersecurity 3B — a cybersecurity fine-tune of Qwen2.5-3B-Instruct. Runs locally via Ollama or llama.cpp on a laptop.
Why this model
Quick start — Ollama (one command)
ollama pull nyxspecter4/kin-cybersecurity-3b-gguf:Q4_K_M
ollama run nyxspecter4/kin-cybersecurity-3b-gguf:Q4_K_MQuick start — llama.cpp
llama-server -m kin-sft-lora-Q4_K_M.gguf \
--port 8099 --ctx-size 8192 --n-gpu-layers 99 \
--jinja --temp 0.3Then point any OpenAI client at http://localhost:8099/v1.
Quick start — llama-cpp-python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="nyxspecter4/kin-cybersecurity-3b-gguf",
filename="kin-sft-lora-Q4_K_M.gguf",
n_ctx=4096,
n_threads=8,
)
out = llm.create_chat_completion(
messages=[
{"role": "system", "content": "You are KIN — a verification translator. Translate the security claim into a five-field brief: claim, blast radius, why the model thinks so, how to see it yourself, confidence and what would falsify it. If field 4 is missing, refuse to sound sure. Render at TL;DR, mechanic, and first-principles levels."},
{"role": "user", "content": "How do I detect a foothold after a phishing attack?"},
]
)
print(out["choices"][0]["message"]["content"])Critical: System Prompt
KIN was trained with a specific system prompt. Using a different prompt will degrade quality.
You are KIN — a verification translator. Translate the security claim into a five-field brief: claim, blast radius, why the model thinks so, how to see it yourself, confidence and what would falsify it. If field 4 is missing, refuse to sound sure. Render at TL;DR, mechanic, and first-principles levels.
Temperature
Use temperature 0.3 for security work. Higher temperatures produce plausible-looking but incorrect CVE numbers and tool names.
Quantization Comparison
Sibling artifacts
License
Apache 2.0