Instructions to use sourcepirate/falcon-h1-tiny-cyber with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sourcepirate/falcon-h1-tiny-cyber with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sourcepirate/falcon-h1-tiny-cyber") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("sourcepirate/falcon-h1-tiny-cyber") model = AutoModelForCausalLM.from_pretrained("sourcepirate/falcon-h1-tiny-cyber", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - PEFT
How to use sourcepirate/falcon-h1-tiny-cyber with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use sourcepirate/falcon-h1-tiny-cyber 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 sourcepirate/falcon-h1-tiny-cyber:Q8_0 # Run inference directly in the terminal: llama cli -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0 # Run inference directly in the terminal: llama cli -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0
Use Docker
docker model run hf.co/sourcepirate/falcon-h1-tiny-cyber:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use sourcepirate/falcon-h1-tiny-cyber with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sourcepirate/falcon-h1-tiny-cyber" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sourcepirate/falcon-h1-tiny-cyber", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/sourcepirate/falcon-h1-tiny-cyber:Q8_0
- SGLang
How to use sourcepirate/falcon-h1-tiny-cyber 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 "sourcepirate/falcon-h1-tiny-cyber" \ --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": "sourcepirate/falcon-h1-tiny-cyber", "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 "sourcepirate/falcon-h1-tiny-cyber" \ --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": "sourcepirate/falcon-h1-tiny-cyber", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use sourcepirate/falcon-h1-tiny-cyber with Ollama:
ollama run hf.co/sourcepirate/falcon-h1-tiny-cyber:Q8_0
- Unsloth Desktop
- Pi
How to use sourcepirate/falcon-h1-tiny-cyber with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "sourcepirate/falcon-h1-tiny-cyber:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use sourcepirate/falcon-h1-tiny-cyber with Docker Model Runner:
docker model run hf.co/sourcepirate/falcon-h1-tiny-cyber:Q8_0
- Lemonade
How to use sourcepirate/falcon-h1-tiny-cyber with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sourcepirate/falcon-h1-tiny-cyber:Q8_0
Run and chat with the model
lemonade run user.falcon-h1-tiny-cyber-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use sourcepirate/falcon-h1-tiny-cyber with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0
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://127.0.0.1:9931/v1 hermes config set model.default sourcepirate/falcon-h1-tiny-cyber:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use sourcepirate/falcon-h1-tiny-cyber with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sourcepirate/falcon-h1-tiny-cyber:Q8_0
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://127.0.0.1:9931/v1 \ --custom-model-id "sourcepirate/falcon-h1-tiny-cyber:Q8_0" \ --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"
Falcon-H1-Tiny-R-90M — cyber-security QLoRA
A QLoRA fine-tune of tiiuae/Falcon-H1-Tiny-R-90M
on public red-team and cyber-security datasets. Weights are merged into the base
model, so this repository loads as a normal causal language model.
Training
| Setting | Value |
|---|---|
| Method | QLoRA (4bit base) + LoRA |
| LoRA rank / alpha / dropout | 8 / 16 / 0.05 |
| LoRA targets | q_proj, k_proj, v_proj, o_proj, in_proj, gate_proj, up_proj, down_proj |
| Learning rate | 0.0002 |
| Epochs | 1 |
| Micro batch x grad accum | 1 x 8 |
| Max sequence length | 1024 (longer rows dropped, not truncated) |
| Optimizer | paged_adamw_8bit |
| Seed | 42 |
Data
| Loader | Source | Rows (cap) |
|---|---|---|
redteam |
WNT3D/Ultimate-Offensive-Red-Team |
20000 |
kali |
suryanshp1/kali-linux-pentesting-data |
343 |
kimi |
echel0nn1881/kimi-cyber-reasoning |
997 |
cti |
reloading0101/threat-intelligence-dataset |
6000 |
exploitdb |
Waiper/ExploitDB_DataSet |
8000 |
linuxcmd |
Romit2004/LinuxCommands |
6000 |
debian |
2etatg/Debian_Hacking_Networking |
965 |
reloading0101/threat-intelligence-dataset is CC-BY-NC-SA-4.0
(non-commercial); check every source before commercial use.
Files
model.safetensors— merged weights (bf16) with the tokenizer and chat template.training_config.json— resolved configuration used for this run.model-q8_0.gguf
Usage
Transformers:
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "sourcepirate/falcon-h1-tiny-cyber"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
messages = [{"role": "user", "content": "Write a tcpdump command for DNS only"}]
inputs = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_tensors="pt", return_dict=True
).to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=128)[0][inputs["input_ids"].shape[-1]:],
skip_special_tokens=True))
llama.cpp (CPU or GPU, no Python):
llama-cli -m model-q8_0.gguf -p "Write a tcpdump command for DNS only" --n-predict 128
Evaluation
Training and per-row evaluation gate on finite loss; no benchmark scores are claimed here. A NaN/inf loss aborts the run instead of publishing an adapter.
Limitations and authorised use
This model is intended for authorised security testing, research and education. It can produce offensive commands and may be wrong; review every output before running it. The base model ships under the Falcon-LLM licence (link), and the merged model inherits it.
- Downloads last month
- 382
Model tree for sourcepirate/falcon-h1-tiny-cyber
Base model
tiiuae/Falcon-H1-Tiny-R-90M