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 Terminal Chat Client β Simple chat interface for JEDI AI. | |
| Works with or without fine-tuned model. | |
| """ | |
| import sys | |
| import os | |
| import json | |
| import time | |
| import hashlib | |
| import textwrap | |
| from datetime import datetime | |
| # Add JEDI to path | |
| sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) | |
| from jedi.core.engine import JEDIEngine, ThreatLevel | |
| from jedi.core.nanobot import Nanobot, NanobotType | |
| from jedi.core.mission import Mission, MissionStatus | |
| 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 | |
| # Try loading the fine-tuned model | |
| MODEL_LOADED = False | |
| model = None | |
| tokenizer = None | |
| def load_model(): | |
| global MODEL_LOADED, model, tokenizer | |
| lora_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "jedi-tiny-lora") | |
| if os.path.exists(lora_path): | |
| try: | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| from peft import PeftModel | |
| print(" Loading JEDI model (TinyLlama 1.1B + LoRA)...") | |
| tokenizer = AutoTokenizer.from_pretrained(lora_path) | |
| base = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0", | |
| torch_dtype="auto", device_map="cpu", low_cpu_mem_usage=True) | |
| model = PeftModel.from_pretrained(base, lora_path) | |
| model.eval() | |
| MODEL_LOADED = True | |
| print(" β JEDI model loaded!") | |
| except Exception as e: | |
| print(f" β Model load failed: {e}") | |
| print(" Falling back to rule-based responses.") | |
| else: | |
| print(" No fine-tuned model found. Using rule-based JEDI.") | |
| def ai_respond(prompt: str) -> str: | |
| """Get response from JEDI AI (model or rule-based).""" | |
| if MODEL_LOADED and model is not None: | |
| try: | |
| formatted = f"<|user|>\n{prompt}\n<|assistant|>\n" | |
| inputs = tokenizer(formatted, return_tensors="pt", truncation=True, max_length=1024) | |
| import torch | |
| with torch.no_grad(): | |
| outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, | |
| do_sample=True, pad_token_id=tokenizer.eos_token_id) | |
| response = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| if "<|assistant|>" in response: | |
| return response.split("<|assistant|>")[-1].strip() | |
| return response | |
| except Exception as e: | |
| return f"[Model error: {e}]" | |
| # Rule-based fallback | |
| return rule_based_respond(prompt) | |
| def rule_based_respond(prompt: str) -> str: | |
| """Rule-based JEDI responses when model isn't loaded.""" | |
| p = prompt.lower() | |
| if any(w in p for w in ["hello", "hi", "hey", "greet"]): | |
| return ("JEDI Online. Joint Entity Defense Infrastructure v0.1.0.\n" | |
| "I'm your cybersecurity nanobot command interface.\n" | |
| "Type 'help' for available commands or 'status' for system report.") | |
| if "status" in p or "screenshot" in p or "situation" in p: | |
| mc = MissionControl() | |
| dash = mc.dashboard() | |
| return (f"βββ JEDI STATUS βββ\n" | |
| f" Engine: {dash['engine_state']}\n" | |
| f" Threat: {dash['threat_level']}\n" | |
| f" Missions: {dash['active_missions']}\n" | |
| f" Nanobots: {dash['deployed_nanobots']}\n" | |
| f" Uptime: {dash['uptime_hours']}h") | |
| if "help" in p: | |
| return ("βββ JEDI COMMANDS βββ\n" | |
| " status β System situation report\n" | |
| " mission β Create a new mission\n" | |
| " deploy β Deploy a nanobot\n" | |
| " scan β Scan a target\n" | |
| " swarm β View swarm status\n" | |
| " threat β Assess a threat\n" | |
| " audit β Run compliance check\n" | |
| " help β This message\n" | |
| " quit β Exit JEDI\n" | |
| "\nYou can also ask me cybersecurity questions directly.") | |
| if "deploy" in p or "nanobot" in p: | |
| return ("Nanobot types available:\n" | |
| " π΄ STRIKER β Offensive (pen test)\n" | |
| " π΅ GUARDIAN β Defensive (monitor)\n" | |
| " π£ SYNAPSE β Combined (coordinate)\n" | |
| " π‘ AUDITOR β Compliance (audit)\n" | |
| " π’ ARCHITECT β Secure dev (review)\n" | |
| " β« GHOST β Covert (attribution)\n" | |
| " π SCOUT β Reconnaissance\n" | |
| " π€ SENTINEL β Perimeter watch\n" | |
| "\nUsage: 'deploy ghost to 10.0.0.1' or ask me to create a mission.") | |
| if "threat" in p or "assess" in p or "risk" in p: | |
| engine = JEDIEngine() | |
| indicators = [] | |
| if "apt" in p or "nation" in p: | |
| indicators.append({"type": "nation_state_attribution", "severity": 40}) | |
| if "malware" in p or "virus" in p or "ransomware" in p: | |
| indicators.append({"type": "ransomware", "severity": 30}) | |
| if "phish" in p: | |
| indicators.append({"type": "social_engineering", "severity": 15}) | |
| if "exfil" in p or "leak" in p: | |
| indicators.append({"type": "data_exfiltration", "severity": 25}) | |
| if "lateral" in p: | |
| indicators.append({"type": "lateral_movement", "severity": 15}) | |
| if not indicators: | |
| indicators.append({"type": "suspicious_process", "severity": 5}) | |
| level = engine.assess_threat({"indicators": indicators, "confidence": 0.7}) | |
| response = f"βββ THREAT ASSESSMENT βββ\n Level: {level.name}\n" | |
| if level.value >= 4: | |
| response += " β CRITICAL β Recommend immediate containment\n" | |
| response += " Deploy Guardian + Sentinel swarm\n" | |
| response += " Activate emergency ROE" | |
| elif level.value >= 3: | |
| response += " β HIGH β Enhanced monitoring recommended\n" | |
| response += " Deploy Guardian nanobot for continuous monitoring" | |
| elif level.value >= 2: | |
| response += " β² MEDIUM β Active monitoring\n" | |
| response += " Sentinel on perimeter, log all anomalies" | |
| else: | |
| response += " β LOW β Normal operations\n" | |
| response += " Continue passive monitoring" | |
| return response | |
| if "scan" in p or "recon" in p or "map" in p: | |
| return ("βββ SCAN PROTOCOL βββ\n" | |
| "To scan a target, I need:\n" | |
| " 1. Target IP/hostname\n" | |
| " 2. Scan type (quick/full/stealth)\n" | |
| " 3. Authorization level\n\n" | |
| "Example: 'scan 192.168.1.0/24 quick'\n" | |
| "I'll deploy a Scout nanobot with appropriate stealth settings.") | |
| if "swarm" in p: | |
| return ("βββ SWARM STATUS βββ\n" | |
| " No active swarm.\n" | |
| " To create one: 'mission create recon 10.0.0.0/24'\n" | |
| " This will deploy a coordinated swarm with\n" | |
| " Scout, Guardian, and Sentinel nanobots.") | |
| if "audit" in p or "compliance" in p or "nist" in p: | |
| gate = LegalGate() | |
| auth = gate.create_authorization("JEDI-CLI", AuthorizationLevel.OBSERVE, | |
| "LOCAL", "CLI-AUTH", "audit", {"address": "localhost"}) | |
| return ("βββ COMPLIANCE AUDIT βββ\n" | |
| " Frameworks available:\n" | |
| " β’ NIST CSF\n" | |
| " β’ ISO 27001\n" | |
| " β’ HIPAA\n" | |
| " β’ FedRAMP\n" | |
| " β’ GDPR\n\n" | |
| " To run: 'audit nist on 10.0.0.1'\n" | |
| " I'll deploy an Auditor nanobot for continuous monitoring.") | |
| if "mission" in p: | |
| return ("βββ MISSION CONTROL βββ\n" | |
| " Create a mission:\n" | |
| " 'mission create <type> <target>'\n\n" | |
| " Types: recon, defense, pentest, attribution, sweep\n\n" | |
| " Example:\n" | |
| " mission create recon 10.0.0.0/24\n" | |
| " mission create pentest webapp.example.com\n" | |
| " mission create attribution 10.0.0.50") | |
| if any(w in p for w in ["quit", "exit", "bye", "shutdown"]): | |
| return "JEDI shutting down. All nanobots self-destructed. Ledger verified. Goodbye." | |
| # Default: provide useful info | |
| return ("I'm JEDI β Joint Entity Defense Infrastructure AI.\n" | |
| "I can help with cybersecurity operations:\n" | |
| " β’ Assess threats and risks\n" | |
| " β’ Plan reconnaissance missions\n" | |
| " β’ Deploy nanobot swarms\n" | |
| " β’ Coordinate red/blue team ops\n" | |
| " β’ Compliance auditing\n" | |
| " β’ Attribution analysis\n\n" | |
| "Type 'help' for commands or ask me anything about cybersecurity.") | |
| BANNER = r""" | |
| βββ ββββββ βββββββ βββ ββββββββββββββ | |
| ββββββββββββββββββββββ ββββββββββββββ | |
| ββββββββββββββββββββββ ββββββββββββββ | |
| ββββββββββββββββββββββββ βββββββββββββββ | |
| βββββββββββ ββββββ βββ βββββββ βββββββββββ | |
| βββββββββββ ββββββ βββ βββββ βββββββββββ | |
| Joint Entity Defense Infrastructure | |
| Cybersecurity Nanobot Command Interface | |
| v0.1.0 β Ferrell Synthetic Intelligence | |
| """ | |
| def main(): | |
| print(BANNER) | |
| print(" Initializing JEDI systems...") | |
| # Load AI model | |
| load_model() | |
| # Initialize systems | |
| engine = JEDIEngine() | |
| gate = LegalGate() | |
| mc = MissionControl(engine) | |
| swarm = SwarmCoordinator("cli-swarm") | |
| comms = CommsChannel("cli-comms") | |
| memory = HelixMemoryStore() | |
| print(f" β Engine: {engine.state.value}") | |
| print(f" β Legal Gate: active") | |
| print(f" β Ledger: {len(engine.ledger.entries)} entries") | |
| print(f" β Swarm: {swarm.get_swarm_status()['total_members']} members") | |
| print(f" β Comms: encrypted") | |
| print(f" β Memory: {memory.get_stats()['total_memories']} entries") | |
| print() | |
| print(" Type 'help' for commands. Type 'quit' to exit.") | |
| print() | |
| # Chat loop | |
| while True: | |
| try: | |
| user_input = input("\033[96m JEDI βΈ \033[0m").strip() | |
| except (EOFError, KeyboardInterrupt): | |
| print("\n\n JEDI shutting down. All nanobots self-destructed.") | |
| break | |
| if not user_input: | |
| continue | |
| # Handle special commands | |
| if user_input.lower() in ["quit", "exit", "bye", "shutdown"]: | |
| print("\n JEDI shutting down. Ledger verified. Goodbye.\n") | |
| break | |
| if user_input.lower() == "clear": | |
| os.system("clear" if os.name != "nt" else "cls") | |
| print(BANNER) | |
| continue | |
| # Get AI response | |
| response = ai_respond(user_input) | |
| # Format and display | |
| print() | |
| for line in response.split("\n"): | |
| wrapped = textwrap.fill(line, width=80, initial_indent=" ", subsequent_indent=" ") | |
| print(wrapped) | |
| # Log to memory | |
| memory.record_episode({ | |
| "type": "cli_interaction", | |
| "input": user_input[:100], | |
| "response_length": len(response), | |
| }) | |
| engine.ledger.log("cli_interaction", {"input": user_input[:50]}) | |
| if __name__ == "__main__": | |
| main() | |