Instructions to use basilmh25/Llama_fine-tune_Cybersecucity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basilmh25/Llama_fine-tune_Cybersecucity with Transformers:

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

pipe = pipeline("text-generation", model="basilmh25/Llama_fine-tune_Cybersecucity")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("basilmh25/Llama_fine-tune_Cybersecucity")
model = AutoModelForCausalLM.from_pretrained("basilmh25/Llama_fine-tune_Cybersecucity")

llama-cpp-python

How to use basilmh25/Llama_fine-tune_Cybersecucity with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="basilmh25/Llama_fine-tune_Cybersecucity",
	filename="llama-3.1-8b.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use basilmh25/Llama_fine-tune_Cybersecucity 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 basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf basilmh25/Llama_fine-tune_Cybersecucity: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 basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf basilmh25/Llama_fine-tune_Cybersecucity: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 basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M

Use Docker

docker model run hf.co/basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M

LM Studio
Jan

vLLM

How to use basilmh25/Llama_fine-tune_Cybersecucity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "basilmh25/Llama_fine-tune_Cybersecucity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basilmh25/Llama_fine-tune_Cybersecucity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M

SGLang

How to use basilmh25/Llama_fine-tune_Cybersecucity 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 "basilmh25/Llama_fine-tune_Cybersecucity" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basilmh25/Llama_fine-tune_Cybersecucity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "basilmh25/Llama_fine-tune_Cybersecucity" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basilmh25/Llama_fine-tune_Cybersecucity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use basilmh25/Llama_fine-tune_Cybersecucity with Ollama:
```
ollama run hf.co/basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M
```

Unsloth Studio

How to use basilmh25/Llama_fine-tune_Cybersecucity 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 basilmh25/Llama_fine-tune_Cybersecucity 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 basilmh25/Llama_fine-tune_Cybersecucity to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for basilmh25/Llama_fine-tune_Cybersecucity to start chatting

Atomic Chat new
Docker Model Runner
How to use basilmh25/Llama_fine-tune_Cybersecucity with Docker Model Runner:
```
docker model run hf.co/basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M
```

Lemonade

How to use basilmh25/Llama_fine-tune_Cybersecucity with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull basilmh25/Llama_fine-tune_Cybersecucity:Q4_K_M

Run and chat with the model

lemonade run user.Llama_fine-tune_Cybersecucity-Q4_K_M

List all available models

lemonade list

CyberSec-LLM

A fine-tuned Llama 3.1 8B Instruct model specialized for cybersecurity assistance.

Overview

This model was fine-tuned using LoRA on the Cybersecurity Dataset Fenrir v2.1. It is designed to help with:

Vulnerability explanation
Secure coding guidance
Incident response
Threat intelligence
Malware analysis (conceptual)
Network security
Linux and Windows security
Web application security

Base Model

Model: Llama 3.1 8B Instruct
Fine-tuning: LoRA
Framework: Unsloth
Inference: llama.cpp / Transformers (compatible after merging or GGUF conversion)

Dataset

Cybersecurity Dataset Fenrir v2.1

Capabilities

Explain cybersecurity concepts
Analyze vulnerabilities
Recommend mitigations
Answer SOC and Blue Team questions
Generate defensive scripts and examples
Explain logs and alerts

Downloads last month: 70

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for basilmh25/Llama_fine-tune_Cybersecucity

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Adapter

(2590)

this model

basilmh25
/

Llama_fine-tune_Cybersecucity