Text Generation
Transformers
GGUF
English
jedi
cybersecurity
nanobot
swarm-intelligence
vitalis
lfm
liquid-foundation-model
lora
qlora
veritas
machiavelli
sovereign-ai
ferrell-synthetic-intelligence
conversational
Instructions to use FerrellSyntheticIntelligence/JEDI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FerrellSyntheticIntelligence/JEDI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FerrellSyntheticIntelligence/JEDI") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FerrellSyntheticIntelligence/JEDI", dtype="auto") - llama-cpp-python
How to use FerrellSyntheticIntelligence/JEDI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="FerrellSyntheticIntelligence/JEDI", filename="model/LFM2.5-1.2B-Instruct-Q4_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use FerrellSyntheticIntelligence/JEDI 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 FerrellSyntheticIntelligence/JEDI:Q4_K_M # Run inference directly in the terminal: llama cli -hf FerrellSyntheticIntelligence/JEDI:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf FerrellSyntheticIntelligence/JEDI:Q4_K_M # Run inference directly in the terminal: llama cli -hf FerrellSyntheticIntelligence/JEDI: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 FerrellSyntheticIntelligence/JEDI:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf FerrellSyntheticIntelligence/JEDI: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 FerrellSyntheticIntelligence/JEDI:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf FerrellSyntheticIntelligence/JEDI:Q4_K_M
Use Docker
docker model run hf.co/FerrellSyntheticIntelligence/JEDI:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use FerrellSyntheticIntelligence/JEDI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FerrellSyntheticIntelligence/JEDI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FerrellSyntheticIntelligence/JEDI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FerrellSyntheticIntelligence/JEDI:Q4_K_M
- SGLang
How to use FerrellSyntheticIntelligence/JEDI 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 "FerrellSyntheticIntelligence/JEDI" \ --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": "FerrellSyntheticIntelligence/JEDI", "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 "FerrellSyntheticIntelligence/JEDI" \ --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": "FerrellSyntheticIntelligence/JEDI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use FerrellSyntheticIntelligence/JEDI with Ollama:
ollama run hf.co/FerrellSyntheticIntelligence/JEDI:Q4_K_M
- Unsloth Studio
How to use FerrellSyntheticIntelligence/JEDI 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 FerrellSyntheticIntelligence/JEDI 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 FerrellSyntheticIntelligence/JEDI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for FerrellSyntheticIntelligence/JEDI to start chatting
- Pi
How to use FerrellSyntheticIntelligence/JEDI with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf FerrellSyntheticIntelligence/JEDI:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "FerrellSyntheticIntelligence/JEDI:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use FerrellSyntheticIntelligence/JEDI with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf FerrellSyntheticIntelligence/JEDI:Q4_K_M
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://127.0.0.1:8080/v1 hermes config set model.default FerrellSyntheticIntelligence/JEDI:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use FerrellSyntheticIntelligence/JEDI with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf FerrellSyntheticIntelligence/JEDI:Q4_K_M
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://127.0.0.1:8080/v1 \ --custom-model-id "FerrellSyntheticIntelligence/JEDI:Q4_K_M" \ --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"
- Docker Model Runner
How to use FerrellSyntheticIntelligence/JEDI with Docker Model Runner:
docker model run hf.co/FerrellSyntheticIntelligence/JEDI:Q4_K_M
- Lemonade
How to use FerrellSyntheticIntelligence/JEDI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull FerrellSyntheticIntelligence/JEDI:Q4_K_M
Run and chat with the model
lemonade run user.JEDI-Q4_K_M
List all available models
lemonade list
| #!/usr/bin/env python3 | |
| """ | |
| JEDI x Vitalis Cortex β Unified CLI | |
| Wires JEDI nanobot framework into Vitalis Cortex LFM2.5 engine. | |
| Runs the full cognitive pipeline: | |
| Quadruflow β Memory β Amplifier β LFM2.5 β Attestation β JEDI modules β Output | |
| """ | |
| import os | |
| import sys | |
| import textwrap | |
| # Paths | |
| BASE = os.path.dirname(os.path.abspath(__file__)) | |
| CORTEX = os.path.join(BASE, "Vitalis_LFM2.5_Cortex.GGUF") | |
| JEDI = BASE | |
| sys.path.insert(0, CORTEX) | |
| sys.path.insert(0, JEDI) | |
| from src.brain.inference import InferenceEngine | |
| from jedi.core.engine import JEDIEngine, ThreatLevel | |
| from jedi.core.nanobot import Nanobot, NanobotType | |
| from jedi.core.mission import Mission | |
| from jedi.legal.gate import LegalGate, AuthorizationLevel | |
| from jedi.swarm.coordinator import SwarmCoordinator | |
| from jedi.command.control import MissionControl | |
| from jedi.comms.channel import CommsChannel | |
| from jedi.memory.helix import HelixMemoryStore | |
| from jedi.nanobots.black.ghost import GhostNanobot | |
| from jedi.nanobots.blue.guardian import GuardianNanobot | |
| from jedi.nanobots.red.striker import StrikerNanobot | |
| from jedi.nanobots.green.architect import ArchitectNanobot | |
| from jedi.nanobots.yellow.auditor import AuditorNanobot | |
| from jedi.nanobots.purple.synapse import SynapseNanobot | |
| BANNER = r""" | |
| ββββββββββββββββββ βββ | |
| ββββββββββββββββββββββ | |
| βββββββββ βββ ββββββ | |
| βββββββββ βββ ββββββ | |
| βββββββββββββββββββββββββββ | |
| ββββββββββββββββββ ββββββββ | |
| βββ βββββββββββββββ ββββββ βββ βββββββββββ | |
| βββ ββββββββββββββββββββββββββ βββββββββββ | |
| βββ ββββββ βββ βββββββββββ βββββββββββ | |
| ββββ βββββββ βββ βββββββββββ βββββββββββ | |
| βββββββ βββ βββ βββ ββββββββββββββββββββββ | |
| βββββ βββ βββ βββ ββββββββββββββββββββββ | |
| JEDI x Vitalis Cortex Hybrid | |
| Nanobot Defense Intelligence | LFM2.5 Cognitive Core | |
| Ferrell Synthetic Intelligence | |
| """ | |
| def main(): | |
| print(BANNER) | |
| print(" Booting JEDI x Vitalis Cortex...\n") | |
| # Initialize JEDI systems | |
| engine = JEDIEngine() | |
| gate = LegalGate() | |
| mc = MissionControl(engine) | |
| swarm = SwarmCoordinator("jedi-swarm") | |
| comms = CommsChannel("jedi-comms") | |
| memory = HelixMemoryStore() | |
| # Initialize Vitalis Cortex with LFM2.5 | |
| try: | |
| cortex = InferenceEngine(model_path=os.path.join(CORTEX, "model", "LFM2.5-1.2B-Instruct-Q4_K_M.gguf")) | |
| print("\n β Vitalis Cortex online β LFM2.5 1.2B cognitive core loaded") | |
| cortex_online = True | |
| except Exception as e: | |
| print(f"\n β Cortex load: {e}") | |
| cortex_online = False | |
| print(" β JEDI Engine online β nanobot framework armed") | |
| print(" β Legal Gate active β all ops require authorization") | |
| print(" β Ledger initialized β immutable audit trail") | |
| print(" β Swarm Coordinator ready") | |
| print() | |
| print(" Type 'help' for commands. Type 'quit' to exit.\n") | |
| memory.record_episode({"type": "session_start", "cortex_online": cortex_online}) | |
| # Chat loop | |
| while True: | |
| try: | |
| prompt = input("\033[96m JEDI βΈ \033[0m").strip() | |
| except (EOFError, KeyboardInterrupt): | |
| print("\n\n Shutdown. All nanobots self-destructed.") | |
| break | |
| if not prompt: | |
| continue | |
| if prompt.lower() in ["quit", "exit", "bye"]: | |
| print("\n JEDI offline. Ledger sealed. Goodbye.\n") | |
| break | |
| if prompt.lower() == "clear": | |
| os.system("clear") | |
| print(BANNER) | |
| continue | |
| # Route to appropriate system | |
| response = route(prompt, cortex if cortex_online else None, engine, gate, mc, swarm, comms, memory) | |
| # Format output | |
| print() | |
| for line in response.split("\n"): | |
| wrapped = textwrap.fill(line, width=80, initial_indent=" ", subsequent_indent=" ") | |
| print(wrapped) | |
| # Log | |
| engine.ledger.log("cli_interaction", {"input": prompt[:80]}) | |
| print() | |
| def route(prompt, cortex, engine, gate, mc, swarm, comms, memory): | |
| """Route prompt to appropriate handler.""" | |
| p = prompt.lower() | |
| # === JEDI COMMANDS === | |
| if any(w in p for w in ["threat", "risk", "assess"]): | |
| return threat_handler(p, engine) | |
| if p.startswith("deploy") or p.startswith("deploy nanobot"): | |
| return deploy_handler(prompt) | |
| if p.startswith("mission"): | |
| return mission_handler(prompt, mc) | |
| if "swarm" in p.split() and len(p.split()) < 4: | |
| return swarm_handler(swarm) | |
| if "scan" in p: | |
| return "βββ SCAN PROTOCOL βββ\nTarget and auth needed. Example:\n mission create recon 10.0.0.0/24\n Then I'll deploy a Scout nanobot swarm." | |
| if p in ["help", "/help", "-h", "--help"]: | |
| return help_text() | |
| if p in ["status", "screenshot"]: | |
| return status_handler(mc) | |
| if p == "clear": | |
| return "" | |
| # Use LLM for anything else | |
| if cortex: | |
| # Inject JEDI context into the cognitive pipeline | |
| context_prompt = f"[JEDI CONTEXT] You are JEDI β Joint Entity Defense Infrastructure. A cybersecurity nanobot command AI. Respond as a tactical cybersecurity operations specialist.\n\nUser: {prompt}" | |
| result = cortex.think(context_prompt, verbose=False) | |
| return result["response"] | |
| return rule_based(prompt) | |
| def help_text(): | |
| return ("βββ JEDI COMMANDS βββ\n" | |
| " help β This message\n" | |
| " status β System situation report\n" | |
| " threat <info> β Assess a threat\n" | |
| " mission create β Create a new mission\n" | |
| " deploy <type> β Deploy a nanobot\n" | |
| " swarm β Swarm status\n" | |
| " scan <target> β Scan a target\n" | |
| " audit <framework> β Compliance check\n" | |
| " quit β Exit\n\n" | |
| "Ask anything else and JEDI uses the LFM2.5 cognitive core.") | |
| def status_handler(mc): | |
| d = mc.dashboard() | |
| return (f"βββ JEDI STATUS βββ\n" | |
| f" Engine: {d['engine_state']}\n" | |
| f" Threat: {d['threat_level']}\n" | |
| f" Missions: {d['active_missions']}\n" | |
| f" Nanobots: {d['deployed_nanobots']}\n" | |
| f" Uptime: {d['uptime_hours']}h") | |
| def threat_handler(p, engine): | |
| ind = [] | |
| if any(w in p for w in ["apt", "nation", "state"]): | |
| ind.append({"type": "nation_state_attribution", "severity": 40}) | |
| if any(w in p for w in ["ransom", "malware"]): | |
| ind.append({"type": "ransomware", "severity": 30}) | |
| if "phish" in p: | |
| ind.append({"type": "social_engineering", "severity": 15}) | |
| if any(w in p for w in ["exfil", "leak"]): | |
| ind.append({"type": "data_exfiltration", "severity": 25}) | |
| if "lateral" in p: | |
| ind.append({"type": "lateral_movement", "severity": 15}) | |
| if not ind: | |
| ind.append({"type": "suspicious_process", "severity": 5}) | |
| level = engine.assess_threat({"indicators": ind, "confidence": 0.7}) | |
| lines = [f"βββ THREAT ASSESSMENT βββ", f" Level: {level.name}"] | |
| if level.value >= 4: | |
| lines.extend([" β CRITICAL β Immediate containment", " Deploy Guardian + Sentinel swarm", " Activate emergency ROE"]) | |
| elif level.value >= 3: | |
| lines.extend([" β HIGH β Enhanced monitoring", " Deploy Guardian nanobot"]) | |
| elif level.value >= 2: | |
| lines.extend([" β² MEDIUM β Active monitoring"]) | |
| else: | |
| lines.extend([" β LOW β Normal ops"]) | |
| return "\n".join(lines) | |
| def deploy_handler(prompt): | |
| bot_types = { | |
| "striker": "π΄ STRIKER β Offensive penetration testing", | |
| "guardian": "π΅ GUARDIAN β Defensive monitoring", | |
| "ghost": "β« GHOST β Covert/attribution (Gov use)", | |
| "synapse": "π£ SYNAPSE β Combined ops coordination", | |
| "auditor": "π‘ AUDITOR β Compliance checking", | |
| "architect": "π’ ARCHITECT β Secure code review", | |
| "scout": "π SCOUT β Reconnaissance", | |
| "sentinel": "π€ SENTINEL β Perimeter watch", | |
| } | |
| return (f"βββ NANOBOTS βββ\n" + | |
| "\n".join(f" {v}" for v in bot_types.values()) + | |
| "\n\nUsage: deploy ghost to 10.0.0.1\nOr just ask the LLM to set up a mission.") | |
| def mission_handler(prompt, mc): | |
| return ("βββ MISSION CONTROL βββ\n" | |
| "Create: mission create <type> <target>\n" | |
| "Types: recon, defense, pentest, attribution, sweep\n\n" | |
| "Example:\n mission create recon 10.0.0.0/24\n mission create pentet webapp.example.com") | |
| def swarm_handler(swarm): | |
| s = swarm.get_swarm_status() | |
| return (f"βββ SWARM STATUS βββ\n" | |
| f" ID: {s['swarm_id']}\n" | |
| f" Members: {s['active_members']}/{s['total_members']}\n" | |
| f" Tasks queued: {s['tasks_queued']}\n" | |
| f" Wisom: {s.get('wisdom_size', {'intel_entries': 0})['intel_entries']} intel entries\n" | |
| f" Decisions: {s['consensus_reached']}\n" | |
| f"\nTo deploy a swarm: create a mission first.") | |
| def rule_based(prompt): | |
| return ("JEDI operational. Your query goes through the LFM2.5 cognitive core\n" | |
| "with Quadruflow routing, memory retrieval, and attestation gating.\n" | |
| "Type 'help' for commands or ask me anything about cybersecurity.\n" | |
| "(Full LLM mode available when the model loads successfully.)") | |
| if __name__ == "__main__": | |
| main() | |