Instructions to use nyxspecter4/kin-cybersecurity-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nyxspecter4/kin-cybersecurity-3b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nyxspecter4/kin-cybersecurity-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nyxspecter4/kin-cybersecurity-3b")
model = AutoModelForCausalLM.from_pretrained("nyxspecter4/kin-cybersecurity-3b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nyxspecter4/kin-cybersecurity-3b 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 nyxspecter4/kin-cybersecurity-3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

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 nyxspecter4/kin-cybersecurity-3b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

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 nyxspecter4/kin-cybersecurity-3b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

Use Docker

docker model run hf.co/nyxspecter4/kin-cybersecurity-3b:Q4_K_M

LM Studio
Jan

vLLM

How to use nyxspecter4/kin-cybersecurity-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nyxspecter4/kin-cybersecurity-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyxspecter4/kin-cybersecurity-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nyxspecter4/kin-cybersecurity-3b:Q4_K_M

SGLang

How to use nyxspecter4/kin-cybersecurity-3b 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 "nyxspecter4/kin-cybersecurity-3b" \
    --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": "nyxspecter4/kin-cybersecurity-3b",
		"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 "nyxspecter4/kin-cybersecurity-3b" \
        --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": "nyxspecter4/kin-cybersecurity-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use nyxspecter4/kin-cybersecurity-3b with Ollama:
```
ollama run hf.co/nyxspecter4/kin-cybersecurity-3b:Q4_K_M
```
Unsloth Desktop

How to use nyxspecter4/kin-cybersecurity-3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

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": "nyxspecter4/kin-cybersecurity-3b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nyxspecter4/kin-cybersecurity-3b with Docker Model Runner:
```
docker model run hf.co/nyxspecter4/kin-cybersecurity-3b:Q4_K_M
```

Lemonade

How to use nyxspecter4/kin-cybersecurity-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nyxspecter4/kin-cybersecurity-3b:Q4_K_M

Run and chat with the model

lemonade run user.kin-cybersecurity-3b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nyxspecter4/kin-cybersecurity-3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

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 nyxspecter4/kin-cybersecurity-3b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nyxspecter4/kin-cybersecurity-3b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nyxspecter4/kin-cybersecurity-3b:Q4_K_M

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 "nyxspecter4/kin-cybersecurity-3b:Q4_K_M" \
  --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"

nyxspecter4 commited on 5 days ago

Commit

7be4e35

verified ·

1 Parent(s): 5d41a6b

docs: model card matches reality — Q4_K_M GGUF now in-repo (1.93 GB) for Ollama llama.cpp one-liners, honest quant matrix with status, record counts corrected (1,637 DPO), limitations section added

Browse files

Files changed (1) hide show

README.md +27 -24

README.md CHANGED Viewed

@@ -24,6 +24,7 @@ tags:
   - conversational
   - llama-cpp
   - gguf
 ---
 # KIN — Cybersecurity Verification Translator (3B)
@@ -35,7 +36,7 @@ KIN is an authoritative, fine-tuned cybersecurity model built on **Qwen2.5-3B-In
 ## Evaluation & Leaderboard Status
 * **Hugging Face Open LLM Leaderboard:** [Job PENDING Evaluation](https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/nyxspecter4/kin-sft-lora_eval_request_False_bfloat16_Original.json)
-* **Downloads:** **1,080+** and climbing
 ---
@@ -91,16 +92,17 @@ print(output[0]["generated_text"])
 ---
-## Quickstart: Ollama & Local GGUF
-KIN is available in both full Safetensors weights and **GGUF** quantization (`Q4_K_M`):
 ```bash
-# Run directly with Ollama from Hugging Face
 ollama run hf.co/nyxspecter4/kin-sft-lora
 ```
-Or using the included `Modelfile`:
 ```bash
 git clone https://huggingface.co/nyxspecter4/kin-sft-lora
 cd kin-sft-lora
@@ -108,6 +110,21 @@ ollama create kin -f Modelfile
 ollama run kin
 ```
 ---
 ## Training Details
@@ -118,26 +135,12 @@ ollama run kin
 | Method | LoRA SFT + DPO Alignment |
 | LoRA Rank / Alpha | 8 / 16 |
 | Target Modules | `q_proj`, `k_proj`, `v_proj`, `o_proj` |
-| Training Dataset | [`nyxspecter4/kin-cyber-dpo-v2`](https://huggingface.co/datasets/nyxspecter4/kin-cyber-dpo-v2) (1,635 curated pairs) |
-| Frameworks | TRL 0.14.0, Transformers 4.48.0, Unsloth, PyTorch 2.6.0+cu124 |
-| Weights | **Full Merged Safetensors** + Standalone GGUF |
 ---
-## Public Ecosystem
-| Artifact | Location | Description |
-|---|---|---|
-| **Training Dataset** | [`nyxspecter4/kin-cyber-dpo-v2`](https://huggingface.co/datasets/nyxspecter4/kin-cyber-dpo-v2) | 1,635 sanitized cybersecurity DPO pairs |
-| **Interactive Demo** | [`nyxspecter4/kin-cybersec`](https://huggingface.co/spaces/nyxspecter4/kin-cybersec) | Live Gradio threat evaluation Space |
----
-## Limitations & Scope
-- **Model Scale (3B)**: Optimized for fast inference, local edge auditing, and triage workflows. For complex multi-step kernel exploitation, pair with human verification.
-- **Always Verify**: KIN provides bold, actionable takes. Use the included verification commands to validate all technical claims before execution.
-## License
-Apache 2.0

   - conversational
   - llama-cpp
   - gguf
+  - qwen
 ---
 # KIN — Cybersecurity Verification Translator (3B)
 ## Evaluation & Leaderboard Status
 * **Hugging Face Open LLM Leaderboard:** [Job PENDING Evaluation](https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/nyxspecter4/kin-sft-lora_eval_request_False_bfloat16_Original.json)
+* **Downloads:** **1,000+** and climbing
 ---
 ---
+## Quickstart: Ollama, GGUF & llama.cpp
+This repo ships the **Q4_K_M GGUF (1.93 GB)** next to the full Safetensors weights, so local CPU/GPU inference is one command:
 ```bash
+# Direct from Hugging Face with Ollama (pulls Q4_K_M from this repo)
 ollama run hf.co/nyxspecter4/kin-sft-lora
 ```
+Or build from the included `Modelfile` (LoRA-adapter path):
 ```bash
 git clone https://huggingface.co/nyxspecter4/kin-sft-lora
 cd kin-sft-lora
 ollama run kin
 ```
+With llama.cpp:
+```bash
+llama-cli -hf nyxspecter4/kin-sft-lora -p "How do I detect credential-dump lateral movement?"
+```
+### Quantization Matrix
+| Quant Format | Precision | File Size | Recommended Hardware | Status |
+|---|---|---|---|---|
+| **Q4_K_M** | 4-bit Medium | **1.93 GB** | Laptops & M1/M2/M3 Macs (fastest) | ✅ In this repo |
+| Q5_K_M | 5-bit Medium | ~2.5 GB | Standard desktops (balanced) | Planned |
+| Q8_0 | 8-bit High | ~3.8 GB | Workstations / servers (max fidelity) | Planned |
+| FP16 | 16-bit Full | ~6.2 GB | GPU VRAM >= 8 GB (uncompressed) | Planned |
 ---
 ## Training Details
 | Method | LoRA SFT + DPO Alignment |
 | LoRA Rank / Alpha | 8 / 16 |
 | Target Modules | `q_proj`, `k_proj`, `v_proj`, `o_proj` |
+| Alignment Data | `nyxspecter4/kin-cyber-dpo-v2` (1,637 DPO pairs) |
 ---
+## Limitations
+- 3B-class model: strong at triage, brief-writing, and checklist enforcement — always validate critical findings with a replayable check or scanner before acting.
+- The five-field brief is a reasoning aid, not a formal audit artifact.
+- Long-context codebases should be pre-filtered (diff/relevant file chunks) before prompting.