Text Generation
Transformers
Safetensors
GGUF
English
text-generation-inference
unsloth
qwen2
trl
deepseek
deepseek-r1
cybersecurity
red-team
blue-team
security
reasoning
chain-of-thought
edge-ai
ollama
llama-cpp
lora
4-bit precision
llm-security
penetration-testing
threat-analysis
mcp-security
ai-safety
offline
air-gapped
conversational
Eval Results (legacy)
Instructions to use Nguuma/security-slm-unsloth-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nguuma/security-slm-unsloth-1.5b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Nguuma/security-slm-unsloth-1.5b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Nguuma/security-slm-unsloth-1.5b", dtype="auto") - llama-cpp-python
How to use Nguuma/security-slm-unsloth-1.5b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Nguuma/security-slm-unsloth-1.5b", filename="security-slm-finetuned.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 Nguuma/security-slm-unsloth-1.5b with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Nguuma/security-slm-unsloth-1.5b # Run inference directly in the terminal: llama-cli -hf Nguuma/security-slm-unsloth-1.5b
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Nguuma/security-slm-unsloth-1.5b # Run inference directly in the terminal: llama-cli -hf Nguuma/security-slm-unsloth-1.5b
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 Nguuma/security-slm-unsloth-1.5b # Run inference directly in the terminal: ./llama-cli -hf Nguuma/security-slm-unsloth-1.5b
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 Nguuma/security-slm-unsloth-1.5b # Run inference directly in the terminal: ./build/bin/llama-cli -hf Nguuma/security-slm-unsloth-1.5b
Use Docker
docker model run hf.co/Nguuma/security-slm-unsloth-1.5b
- LM Studio
- Jan
- vLLM
How to use Nguuma/security-slm-unsloth-1.5b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Nguuma/security-slm-unsloth-1.5b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Nguuma/security-slm-unsloth-1.5b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Nguuma/security-slm-unsloth-1.5b
- SGLang
How to use Nguuma/security-slm-unsloth-1.5b 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 "Nguuma/security-slm-unsloth-1.5b" \ --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": "Nguuma/security-slm-unsloth-1.5b", "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 "Nguuma/security-slm-unsloth-1.5b" \ --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": "Nguuma/security-slm-unsloth-1.5b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use Nguuma/security-slm-unsloth-1.5b with Ollama:
ollama run hf.co/Nguuma/security-slm-unsloth-1.5b
- Unsloth Studio new
How to use Nguuma/security-slm-unsloth-1.5b 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 Nguuma/security-slm-unsloth-1.5b 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 Nguuma/security-slm-unsloth-1.5b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Nguuma/security-slm-unsloth-1.5b to start chatting
- Docker Model Runner
How to use Nguuma/security-slm-unsloth-1.5b with Docker Model Runner:
docker model run hf.co/Nguuma/security-slm-unsloth-1.5b
- Lemonade
How to use Nguuma/security-slm-unsloth-1.5b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Nguuma/security-slm-unsloth-1.5b
Run and chat with the model
lemonade run user.security-slm-unsloth-1.5b-{{QUANT_TAG}}List all available models
lemonade list
Extra Model in Repo
1
#1 opened about 2 months ago
by
sillykiwi