Instructions to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Transformers:

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

pipe = pipeline("text-generation", model="reaperdoesntknow/LFM2.5-2.6B-CyberSec")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reaperdoesntknow/LFM2.5-2.6B-CyberSec")
model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/LFM2.5-2.6B-CyberSec", 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 reaperdoesntknow/LFM2.5-2.6B-CyberSec 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 reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec: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 reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec: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 reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

Use Docker

docker model run hf.co/reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

LM Studio
Jan

vLLM

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reaperdoesntknow/LFM2.5-2.6B-CyberSec"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reaperdoesntknow/LFM2.5-2.6B-CyberSec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

SGLang

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec 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 "reaperdoesntknow/LFM2.5-2.6B-CyberSec" \
    --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": "reaperdoesntknow/LFM2.5-2.6B-CyberSec",
		"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 "reaperdoesntknow/LFM2.5-2.6B-CyberSec" \
        --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": "reaperdoesntknow/LFM2.5-2.6B-CyberSec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Ollama:
```
ollama run hf.co/reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M
```

Unsloth Studio

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for reaperdoesntknow/LFM2.5-2.6B-CyberSec to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for reaperdoesntknow/LFM2.5-2.6B-CyberSec to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for reaperdoesntknow/LFM2.5-2.6B-CyberSec to start chatting

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec: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 "reaperdoesntknow/LFM2.5-2.6B-CyberSec: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"

Docker Model Runner
How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Docker Model Runner:
```
docker model run hf.co/reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M
```

Lemonade

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-2.6B-CyberSec-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use reaperdoesntknow/LFM2.5-2.6B-CyberSec with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec: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 reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

Run Hermes

hermes

Atomic Chat

LFM2.5-2.6B-CyberSec

An English LFM2.5 2.6B checkpoint associated with the Trendyol Cybersecurity Instruction Tuning Dataset. This repository contains both Transformers-format model files and local GGUF exports.

This is a research release. The repository does not currently publish benchmark, baseline-comparison, or safety-evaluation results.

Lineage

Base model: LiquidAI/LFM2.5-2.6B
Dataset recorded in metadata: Trendyol/Trendyol-Cybersecurity-Instruction-Tuning-Dataset
Formats: Transformers / Safetensors and GGUF
License: Apache-2.0

Repository formats

Transformers assets include model.safetensors, configuration files, tokenizer files, and a chat template.

GGUF exports include:

F16
Q8_0
Q4_K_M

Keeping both formats in one repository is convenient, but users should explicitly choose the path that matches their runtime.

Transformers usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "reaperdoesntknow/LFM2.5-2.6B-CyberSec"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Explain defense in depth in plain language."}
]
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=256)
answer = outputs[0][inputs["input_ids"].shape[-1]:]
print(tokenizer.decode(answer, skip_special_tokens=True))

The checked configuration includes a bitsandbytes quantization block. Pin and test the exact Transformers, Accelerate, bitsandbytes, and device environment you intend to use.

GGUF usage

With a recent llama.cpp build:

llama-cli \
  -hf reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M \
  --jinja

With Ollama:

ollama run hf.co/reaperdoesntknow/LFM2.5-2.6B-CyberSec:Q4_K_M

Intended use

Research on small-model responses to cybersecurity instruction prompts.
Local qualitative testing and format comparison.
Comparison with the unchanged LiquidAI base model.
Evaluation-harness and inference-runtime development.

Evaluation status

The dataset tag and exported files are observed. Improved cybersecurity ability is not established by those facts alone.

Evidence needed for a stronger release claim includes:

A held-out test split and unchanged-base baseline.
Named cybersecurity and general-capability benchmarks.
Reproducible harness, seed, prompts, and model revision hashes.
Safety, misuse, and hallucination evaluation.
Separate results for the Transformers model and each GGUF quantization.

Limitations and safety

The model can produce incorrect, outdated, insecure, or harmful instructions.
Cybersecurity material is inherently dual use.
The public files reviewed for this card do not document preprocessing, contamination checks, full training hyperparameters, or checkpoint-selection criteria.
Quantized builds can behave differently from the Transformers checkpoint.
Do not execute generated commands without review and isolation.
Do not use this model as the sole basis for incident response, vulnerability disclosure, access control, or other consequential decisions.

Part of the CIx cybersecurity model collection.