Instructions to use cozyiii/llama-aingfw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cozyiii/llama-aingfw with Transformers:

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

pipe = pipeline("text-generation", model="cozyiii/llama-aingfw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cozyiii/llama-aingfw")
model = AutoModelForCausalLM.from_pretrained("cozyiii/llama-aingfw")
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

vLLM

How to use cozyiii/llama-aingfw with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cozyiii/llama-aingfw

SGLang

How to use cozyiii/llama-aingfw 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 "cozyiii/llama-aingfw" \
    --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": "cozyiii/llama-aingfw",
		"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 "cozyiii/llama-aingfw" \
        --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": "cozyiii/llama-aingfw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cozyiii/llama-aingfw with Docker Model Runner:
```
docker model run hf.co/cozyiii/llama-aingfw
```

llama-aingfw

Fine-tuned Llama model for network intrusion detection classification.

Description

This model was fine-tuned for network intrusion detection tasks using structured network flow features.

The model classifies traffic into:

normal
dos
bruteforce
web_attack
botnet
reconnaissance
other_attack

Base Architecture

LlamaForCausalLM
Transformers

Example Prompt

Network Intrusion Detection Task

Classify into: normal, dos, bruteforce, web_attack, botnet, reconnaissance, other_attack

Features: Port: 80 Duration: 1000 Fwd Packets: 10 Bwd Packets: 8 Bytes/s: 500 Packets/s: 20 SYN: 1 ACK: 1 RST: 0

Answer:

Intended Use

Research, testing, and educational demonstrations of AI-assisted network intrusion detection systems.

Downloads last month: 106

Safetensors

Model size

8B params

Tensor type

F16