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
| """ | |
| JEDI Core Engine — The Brain of the Swarm | |
| Integrates: | |
| - Strategic planning (LLM-based) | |
| - Swarm coordination (multi-agent RL) | |
| - Threat analysis (pattern recognition) | |
| - Legal gate (authorization enforcement) | |
| Inspired by: Vitalis Cognitive Substrate + FSI_FELON Chimera | |
| """ | |
| import json | |
| import time | |
| import threading | |
| import hashlib | |
| from enum import Enum | |
| from typing import Optional, Dict, List, Any | |
| from datetime import datetime | |
| class EngineState(Enum): | |
| IDLE = "idle" | |
| PLANNING = "planning" | |
| DEPLOYING = "deploying" | |
| ACTIVE = "active" | |
| PAUSED = "paused" | |
| EMERGENCY = "emergency" | |
| SHUTDOWN = "shutdown" | |
| class ThreatLevel(Enum): | |
| NONE = 0 | |
| LOW = 1 | |
| MEDIUM = 2 | |
| HIGH = 3 | |
| CRITICAL = 4 | |
| NATION_STATE = 5 | |
| class JEDIEngine: | |
| """ | |
| The JEDI Core AI Engine coordinates all nanobot operations. | |
| Architecture: | |
| - Strategic Planner: Mission decomposition and resource allocation | |
| - Swarm Coordinator: Multi-agent orchestration and consensus | |
| - Threat Analyzer: Pattern recognition and adversary profiling | |
| - Legal Gate: Authorization verification and rules of engagement | |
| """ | |
| def __init__(self, config: Optional[Dict] = None): | |
| self.config = config or self._default_config() | |
| self.state = EngineState.IDLE | |
| self.threat_level = ThreatLevel.NONE | |
| self.ledger = Ledger() | |
| self.active_missions = {} | |
| self.deployed_nanobots = {} | |
| self.swarm_memory = SwarmMemory() | |
| self._lock = threading.Lock() | |
| self._start_time = time.time() | |
| self.ledger.log("engine_init", { | |
| "version": "0.1.0", | |
| "config": self.config, | |
| "timestamp": datetime.utcnow().isoformat() | |
| }) | |
| def _default_config(self) -> Dict: | |
| return { | |
| "max_nanobots": 1000, | |
| "max_concurrent_missions": 10, | |
| "heartbeat_interval": 30, | |
| "self_destruct_timeout": 3600, | |
| "legal_gate_required": True, | |
| "human_in_loop": True, | |
| "swarm_consensus_threshold": 0.7, | |
| "threat_auto_escalate": True, | |
| "encryption": "post_quantum", | |
| "audit_all_actions": True, | |
| } | |
| def assess_threat(self, intel: Dict) -> ThreatLevel: | |
| """Analyze incoming intelligence and assess threat level.""" | |
| indicators = intel.get("indicators", []) | |
| confidence = intel.get("confidence", 0.0) | |
| score = 0 | |
| for indicator in indicators: | |
| itype = indicator.get("type", "") | |
| severity = indicator.get("severity", 0) | |
| if itype == "nation_state_attribution": | |
| score += 50 | |
| elif itype == "apt_group": | |
| score += 35 | |
| elif itype == "ransomware": | |
| score += 30 | |
| elif itype == "data_exfiltration": | |
| score += 25 | |
| elif itype == "lateral_movement": | |
| score += 15 | |
| elif itype == "suspicious_process": | |
| score += 10 | |
| elif itype == "anomalous_traffic": | |
| score += 5 | |
| score += severity | |
| score *= confidence | |
| if score >= 80: | |
| self.threat_level = ThreatLevel.NATION_STATE | |
| elif score >= 60: | |
| self.threat_level = ThreatLevel.CRITICAL | |
| elif score >= 40: | |
| self.threat_level = ThreatLevel.HIGH | |
| elif score >= 20: | |
| self.threat_level = ThreatLevel.MEDIUM | |
| elif score >= 5: | |
| self.threat_level = ThreatLevel.LOW | |
| else: | |
| self.threat_level = ThreatLevel.NONE | |
| self.ledger.log("threat_assessment", { | |
| "score": score, | |
| "level": self.threat_level.name, | |
| "indicators_count": len(indicators) | |
| }) | |
| return self.threat_level | |
| def create_mission(self, mission_config: Dict) -> Dict: | |
| """Create a new mission with legal gate verification.""" | |
| if self.config["legal_gate_required"]: | |
| from ..legal.gate import LegalGate | |
| gate = LegalGate() | |
| auth_result = gate.verify_authorization(mission_config) | |
| if not auth_result["authorized"]: | |
| return { | |
| "error": "Authorization denied", | |
| "reason": auth_result["reason"], | |
| "required": auth_result["required_level"] | |
| } | |
| mission_id = hashlib.sha256( | |
| f"{time.time()}_{json.dumps(mission_config)}".encode() | |
| ).hexdigest()[:16] | |
| mission = { | |
| "id": mission_id, | |
| "config": mission_config, | |
| "status": "created", | |
| "created_at": datetime.utcnow().isoformat(), | |
| "nanobots_deployed": [], | |
| "intel_collected": [], | |
| "actions_taken": [], | |
| "authorization": auth_result if self.config["legal_gate_required"] else {"authorized": True}, | |
| } | |
| with self._lock: | |
| self.active_missions[mission_id] = mission | |
| self.ledger.log("mission_created", { | |
| "mission_id": mission_id, | |
| "type": mission_config.get("type", "unknown"), | |
| "target": mission_config.get("target", "unknown") | |
| }) | |
| return mission | |
| def deploy_nanobot(self, nanobot_type: str, mission_id: str, target: Dict) -> Dict: | |
| """Deploy a nanobot to a target.""" | |
| from .nanobot import Nanobot, NanobotType | |
| if mission_id not in self.active_missions: | |
| return {"error": "Mission not found"} | |
| mission = self.active_missions[mission_id] | |
| if mission["status"] == "paused": | |
| return {"error": "Mission is paused"} | |
| bot = Nanobot( | |
| nanobot_type=NanobotType(nanobot_type), | |
| mission_id=mission_id, | |
| target=target | |
| ) | |
| with self._lock: | |
| self.deployed_nanobots[bot.id] = bot | |
| mission["nanobots_deployed"].append(bot.id) | |
| self.ledger.log("nanobot_deployed", { | |
| "bot_id": bot.id, | |
| "type": nanobot_type, | |
| "mission_id": mission_id, | |
| "target": target.get("address", "unknown") | |
| }) | |
| return { | |
| "bot_id": bot.id, | |
| "type": nanobot_type, | |
| "status": "deployed", | |
| "mission_id": mission_id | |
| } | |
| def get_situation_report(self) -> Dict: | |
| """Generate a comprehensive situation report.""" | |
| uptime = time.time() - self._start_time | |
| return { | |
| "engine_state": self.state.value, | |
| "threat_level": self.threat_level.name, | |
| "uptime_seconds": round(uptime, 1), | |
| "active_missions": len(self.active_missions), | |
| "deployed_nanobots": len(self.deployed_nanobots), | |
| "mission_details": { | |
| mid: { | |
| "status": m["status"], | |
| "nanobots": len(m["nanobots_deployed"]), | |
| "intel_count": len(m["intel_collected"]), | |
| "actions": len(m["actions_taken"]) | |
| } | |
| for mid, m in self.active_missions.items() | |
| }, | |
| "nanobot_status": { | |
| bid: { | |
| "type": b.nanobot_type.value, | |
| "state": b.state, | |
| "uptime": round(time.time() - b.deploy_time, 1) | |
| } | |
| for bid, b in self.deployed_nanobots.items() | |
| }, | |
| "ledger_entries": len(self.ledger.entries), | |
| "config": self.config | |
| } | |
| def emergency_shutdown(self, reason: str): | |
| """Emergency shutdown of all operations.""" | |
| self.state = EngineState.SHUTDOWN | |
| with self._lock: | |
| for bot_id, bot in self.deployed_nanobots.items(): | |
| bot.self_destruct() | |
| for mission_id, mission in self.active_missions.items(): | |
| mission["status"] = "emergency_shutdown" | |
| self.ledger.log("emergency_shutdown", { | |
| "reason": reason, | |
| "nanobots_terminated": len(self.deployed_nanobots), | |
| "missions_aborted": len(self.active_missions) | |
| }) | |
| class Ledger: | |
| """ | |
| Cryptographic Conscience — Immutable audit trail. | |
| Inspired by Vitalis Core's Ledger system. | |
| Every action is SHA-256 hashed and chained. | |
| """ | |
| def __init__(self): | |
| self.entries = [] | |
| self._previous_hash = "0" * 64 | |
| def log(self, event_type: str, data: Dict): | |
| entry = { | |
| "timestamp": datetime.utcnow().isoformat(), | |
| "event_type": event_type, | |
| "data": data, | |
| "previous_hash": self._previous_hash, | |
| } | |
| entry_str = json.dumps(entry, sort_keys=True) | |
| entry["hash"] = hashlib.sha256(entry_str.encode()).hexdigest() | |
| self._previous_hash = entry["hash"] | |
| self.entries.append(entry) | |
| def verify_integrity(self) -> bool: | |
| """Verify the entire ledger chain is unbroken.""" | |
| previous = "0" * 64 | |
| for entry in self.entries: | |
| if entry["previous_hash"] != previous: | |
| return False | |
| check = {k: v for k, v in entry.items() if k != "hash"} | |
| check_str = json.dumps(check, sort_keys=True) | |
| if hashlib.sha256(check_str.encode()).hexdigest() != entry["hash"]: | |
| return False | |
| previous = entry["hash"] | |
| return True | |
| def export(self) -> List[Dict]: | |
| return list(self.entries) | |
| class SwarmMemory: | |
| """ | |
| Shared memory across all nanobots in the swarm. | |
| Uses consensus-based writes to prevent corruption. | |
| """ | |
| def __init__(self): | |
| self.store = {} | |
| self._lock = threading.Lock() | |
| self._write_votes = {} | |
| def read(self, key: str) -> Optional[Any]: | |
| with self._lock: | |
| return self.store.get(key) | |
| def write(self, key: str, value: Any, voter_id: str): | |
| """Consensus-based write — requires multiple nanobot votes.""" | |
| with self._lock: | |
| if key not in self._write_votes: | |
| self._write_votes[key] = {} | |
| self._write_votes[key][voter_id] = value | |
| if len(self._write_votes[key]) >= 3: | |
| from collections import Counter | |
| values = list(self._write_votes[key].values()) | |
| most_common = Counter([json.dumps(v, sort_keys=True) for v in values]).most_common(1)[0] | |
| self.store[key] = json.loads(most_common[0]) | |
| del self._write_votes[key] | |
| def snapshot(self) -> Dict: | |
| with self._lock: | |
| return dict(self.store) | |