Instructions to use pki/nova-8b-cybersec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pki/nova-8b-cybersec with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pki/nova-8b-cybersec",
	filename="dolphin3-8b-nova.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use pki/nova-8b-cybersec with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pki/nova-8b-cybersec
# Run inference directly in the terminal:
llama-cli -hf pki/nova-8b-cybersec

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pki/nova-8b-cybersec
# Run inference directly in the terminal:
llama-cli -hf pki/nova-8b-cybersec

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 pki/nova-8b-cybersec
# Run inference directly in the terminal:
./llama-cli -hf pki/nova-8b-cybersec

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 pki/nova-8b-cybersec
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pki/nova-8b-cybersec

Use Docker

docker model run hf.co/pki/nova-8b-cybersec

LM Studio
Jan

vLLM

How to use pki/nova-8b-cybersec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pki/nova-8b-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": "pki/nova-8b-cybersec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pki/nova-8b-cybersec

Ollama
How to use pki/nova-8b-cybersec with Ollama:
```
ollama run hf.co/pki/nova-8b-cybersec
```

Unsloth Studio new

How to use pki/nova-8b-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 pki/nova-8b-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 pki/nova-8b-cybersec to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pki/nova-8b-cybersec to start chatting

Docker Model Runner
How to use pki/nova-8b-cybersec with Docker Model Runner:
```
docker model run hf.co/pki/nova-8b-cybersec
```

Lemonade

How to use pki/nova-8b-cybersec with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pki/nova-8b-cybersec

Run and chat with the model

lemonade run user.nova-8b-cybersec-{{QUANT_TAG}}

List all available models

lemonade list

nova-8b-cybersec

Fine-tuned Dolphin3.0-Llama3.1-8B for cybersecurity tasks.

Model Details

Base Model: cognitivecomputations/Dolphin3.0-Llama3.1-8B
Fine-tuning: QLoRA (rank 64, alpha 128)
Training Examples: 40,075
Context Length: 8192 tokens
Format: ChatML

Training Data

Dataset	Examples
SecurityGPT	16,000
PKI Context QA	16,278
Document Summaries	2,720
Elbranschen Threats	3,386
ISO 27001 Controls	1,116
ISO 27005 Threats	576

Usage

Ollama

ollama run pki/nova-8b-cybersec

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("pki/nova-8b-cybersec")
tokenizer = AutoTokenizer.from_pretrained("pki/nova-8b-cybersec")

Files

model-*.safetensors - Model weights (4 shards)
dolphin3-8b-nova.gguf - GGUF format for Ollama/llama.cpp
tokenizer.json - Tokenizer

Training Config

Epochs: 5
Batch size: 2 (effective 40 with gradient accumulation)
Learning rate: 5e-5
LoRA rank: 64, alpha: 128
Hardware: RTX 3090 24GB

License

Apache 2.0

Downloads last month: 16

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for pki/nova-8b-cybersec

Base model

meta-llama/Llama-3.1-8B

Finetuned

dphn/Dolphin3.0-Llama3.1-8B

Quantized

(23)

this model

Quantizations

2 models