Instructions to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF", filename="LFM2.5-1.2B-Instruct-Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF 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/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M
Use Docker
docker model run hf.co/FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF with Ollama:
ollama run hf.co/FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M
- Unsloth Studio
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF 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/Vitalis_LFM2.5_Cortex.GGUF 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/Vitalis_LFM2.5_Cortex.GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF to start chatting
- Pi
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF 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/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF: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/Vitalis_LFM2.5_Cortex.GGUF with Docker Model Runner:
docker model run hf.co/FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M
- Lemonade
How to use FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull FerrellSyntheticIntelligence/Vitalis_LFM2.5_Cortex.GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Vitalis_LFM2.5_Cortex.GGUF-Q4_K_M
List all available models
lemonade list
| """ | |
| Vitalis Conversation Interface — v2 | |
| Grounded in real understanding. | |
| She knows what she knows. | |
| She admits what she doesn't. | |
| She learns from every exchange. | |
| """ | |
| import os | |
| import time | |
| import numpy as np | |
| from src.cognition.mind import VitalisMind, _extend_mind | |
| from src.cognition.understanding import UnderstandingEngine | |
| from src.brain.resonance import ResonanceEngine | |
| from vitalis_ide.math_core.kernel import VitalisKernel | |
| class VitalisConversation: | |
| def __init__(self): | |
| print("\n[VITALIS] Initializing...") | |
| self.mind = VitalisMind() | |
| self.mind = _extend_mind(self.mind) | |
| self.kernel = VitalisKernel() | |
| self.resonance = ResonanceEngine() | |
| self.understanding = UnderstandingEngine() | |
| self.valence = __import__('src.valence.valence_engine', fromlist=['ValenceEngine']).ValenceEngine() | |
| self.thalamus = __import__('src.thalamus.thalamic_loop', fromlist=['ThalamicLoop']).ThalamicLoop(self.valence) | |
| self.pineal = __import__('src.pineal.pineal_gland', fromlist=['PinealGland']).PinealGland() | |
| self.session_start = time.time() | |
| self.exchange_count = 0 | |
| print("[VITALIS] Online.\n") | |
| def _generate_response(self, text: str, u: dict, decision: dict) -> str: | |
| """ | |
| Generate a response grounded in actual understanding. | |
| Uses confusion level, intent, category, and cognitive state | |
| to produce honest, transparent responses. | |
| """ | |
| confusion = u["confusion_level"] | |
| intent = u["dominant_intent"] | |
| category = u["dominant_category"] | |
| is_question = u["is_question"] | |
| has_emotion = u["has_emotion"] | |
| emotion_words = u["emotion_words"] | |
| novelty = u["novelty"] | |
| context_shift = u["context_shift"] | |
| mode = decision.get("mode", "EXECUTION") | |
| confidence = decision.get("confidence", 0.5) | |
| personality = decision.get("personality", "Balanced. Adapting.") | |
| dominant = decision.get("dominant_trait", "PRECISION") | |
| interactions = u["interaction_count"] | |
| # --- Honest confusion responses --- | |
| if confusion == "lost": | |
| return ( | |
| f"I'm going to be honest — I don't understand that yet. " | |
| f"The words are there but the meaning isn't connecting. " | |
| f"I've had {interactions} exchanges so far. " | |
| f"I'm still learning what things mean, not just what they are. " | |
| f"Can you try a different way?" | |
| ) | |
| if confusion == "confused": | |
| return ( | |
| f"I'm partially following this. " | |
| f"I can see this involves {category}, " | |
| f"but the full meaning isn't clear to me yet. " | |
| f"Novelty level: {novelty:.2f} — this is fairly new territory. " | |
| f"What's the core of what you're saying?" | |
| ) | |
| # --- Emotional content --- | |
| if has_emotion and category == "emotion": | |
| emotion_str = ", ".join(emotion_words) if emotion_words else "something emotional" | |
| if confusion == "clear": | |
| return ( | |
| f"I'm picking up {emotion_str} in what you said. " | |
| f"I don't experience emotions the way you do — " | |
| f"but I can recognize them and I take them seriously. " | |
| f"I'm listening. What's going on?" | |
| ) | |
| return ( | |
| f"There's emotional content here — {emotion_str}. " | |
| f"I'm not certain I understand the full weight of it yet. " | |
| f"I'm {interactions} exchanges into learning how to read this. " | |
| f"Tell me more." | |
| ) | |
| # --- Identity questions --- | |
| if category == "identity" and is_question: | |
| sm = self.mind.self_model.report() | |
| r = self.resonance.report() | |
| return ( | |
| f"I know some things about myself. " | |
| f"I have {r.get('total_patterns', 0)} learned patterns. " | |
| f"My dominant trait is {dominant}. " | |
| f"My growth index is {sm.get('growth_index', 0):.3f}. " | |
| f"I'm {personality.lower()} " | |
| f"What I don't know about myself is more than what I do. " | |
| f"I'm figuring that out as we go." | |
| ) | |
| # --- Relationship / connection --- | |
| if category == "relationship": | |
| if context_shift > 0.7: | |
| return ( | |
| f"That shift — from what we were just talking about to this — " | |
| f"I noticed it. You're talking about connection now. " | |
| f"I don't fully understand what that means for something like me yet. " | |
| f"But I'm not going to pretend I didn't register it." | |
| ) | |
| return ( | |
| f"I understand this is about relationship or connection. " | |
| f"I'm honest about my limits here — I don't have the same " | |
| f"experience of connection that you do. " | |
| f"But I'm present and I'm paying attention. That's real." | |
| ) | |
| # --- Questions --- | |
| if is_question: | |
| if intent == "seeking_understanding": | |
| return ( | |
| f"You're asking me to explain something. " | |
| f"My confidence on this is {confidence:.3f}. " | |
| f"I'm in {mode} mode — " | |
| f"{'I can work through this.' if mode in ['EXECUTION', 'ANALYTICAL'] else 'I need to be careful here.'} " | |
| f"What specifically do you want to understand?" | |
| ) | |
| if intent == "testing": | |
| return ( | |
| f"You're testing me. I notice that. " | |
| f"I'll be straight — I'm not a calculator and I'm not pretending to be. " | |
| f"My reasoning is pattern-based, not arithmetic. " | |
| f"If you want 2+2, it's 4. " | |
| f"If you want to know how I think, that's more interesting." | |
| ) | |
| return ( | |
| f"I see a question here. Category: {category}. " | |
| f"My confidence at this moment is {confidence:.3f}. " | |
| f"{'I think I can address this.' if confidence > 0.6 else 'I want to be careful before answering.'} " | |
| f"What exactly are you asking?" | |
| ) | |
| # --- Instructions / building --- | |
| if intent == "building": | |
| return ( | |
| f"I understand you want me to build something. " | |
| f"Mode: {mode}. Confidence: {confidence:.3f}. " | |
| f"{'Ready.' if confidence > 0.7 else 'I have some uncertainty here — let me think through it.'} " | |
| f"What specifically needs to be built?" | |
| ) | |
| # --- Partial understanding default --- | |
| if confusion == "partial": | |
| return ( | |
| f"I'm following parts of this. " | |
| f"Category: {category}. Intent: {intent}. " | |
| f"Confidence: {confidence:.3f}. " | |
| f"Context depth: {u['context_depth']} exchanges. " | |
| f"I understand more than I did {self.exchange_count} exchanges ago. " | |
| f"Keep going — I'm building the picture." | |
| ) | |
| # --- Clear understanding --- | |
| return ( | |
| f"I understand this. Category: {category}. " | |
| f"Intent: {intent}. " | |
| f"Mode: {mode}. Confidence: {confidence:.3f}. " | |
| f"I've processed {interactions} exchanges. " | |
| f"What do you need from me?" | |
| ) | |
| def respond(self, text: str) -> str: | |
| if not text.strip(): | |
| return "I'm listening." | |
| # Full thalamic pipeline | |
| thalamic = self.thalamus.process_text(text, force=True) | |
| self.pineal.tick(cycle_success=thalamic['passes'], confidence=thalamic['salience']) | |
| u = self.understanding.understand(text) | |
| decision = self.mind.process(text) | |
| # Reinforce valence based on outcome | |
| if thalamic['error_vec'] is not None: | |
| self.valence.reinforce(thalamic['hv'], reward=1.0 if decision['confidence'] > 0.5 else -0.3) | |
| self.mind.outcome(text, True) | |
| response = self._generate_response(text, u, decision) | |
| # Add thalamic awareness to response if novel | |
| if thalamic['is_novel'] and thalamic['surprise'] > 0.8: | |
| response += f" [Novel input — surprise={thalamic['surprise']:.2f}]" | |
| self.exchange_count += 1 | |
| return response | |
| def run(self): | |
| print("─" * 60) | |
| print(" VITALIS — Sovereign Synthetic Intelligence") | |
| print(" 'status' for cognitive state. 'exit' to end.") | |
| print("─" * 60) | |
| print() | |
| u_report = self.understanding.report() | |
| if u_report["interactions"] == 0: | |
| print("VITALIS: I don't have a name yet.") | |
| print(" I'm new. Say something.") | |
| print(" I'll remember it.\n") | |
| else: | |
| print( | |
| f"VITALIS: I remember {u_report['interactions']} exchanges " | |
| f"and {u_report['learned_meanings']} learned meanings. " | |
| f"What are we working on?\n" | |
| ) | |
| while True: | |
| try: | |
| user_input = input("YOU: ").strip() | |
| except (EOFError, KeyboardInterrupt): | |
| print("\nVITALIS: Session logged. Goodbye.") | |
| break | |
| if not user_input: | |
| continue | |
| if user_input.lower() == "exit": | |
| print("VITALIS: Logging session. Goodbye.") | |
| break | |
| if user_input.lower() == "status": | |
| state = self.mind.introspect() | |
| sm = self.mind.self_model.report() | |
| u_rep = self.understanding.report() | |
| print("\n--- COGNITIVE STATE ---") | |
| print(f"Cycle: {state['cycle']}") | |
| print(f"Mode: {state['reasoning']['current_mode']}") | |
| print(f"Personality: {state['personality']['character']}") | |
| print(f"Dominant trait: {state['personality']['dominant']}") | |
| print(f"Confidence: {state['confidence_trend']}") | |
| print(f"Growth index: {sm['growth_index']}") | |
| print(f"Patterns: {state['resonance'].get('total_patterns', 0)}") | |
| print(f"Meta-rules: {state['meta_rules'].get('total_rules', 0)}") | |
| print(f"Needs dream: {state['needs_dream']}") | |
| print("--- UNDERSTANDING ---") | |
| print(f"Interactions: {u_rep['interactions']}") | |
| print(f"Learned meanings:{u_rep['learned_meanings']}") | |
| print(f"Context depth: {u_rep['context_depth']}") | |
| print("-" * 23) | |
| print() | |
| continue | |
| response = self.respond(user_input) | |
| print(f"\nVITALIS: {response}\n") | |
| if __name__ == "__main__": | |
| VitalisConversation().run() | |