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
| """ | |
| Adaptive Curriculum — Vitalis FSI | |
| This is the training heart. | |
| Every cycle: pick a domain, pick a complexity tier, generate a task. | |
| Every output: a real module written to generated/. | |
| Each module is more complex than the last. | |
| Domains rotate so she builds breadth AND depth. | |
| Domains covered: | |
| - Systems engineering | |
| - Software architecture | |
| - Programming patterns | |
| - Framework design | |
| - Security engineering | |
| - Data engineering | |
| - Distributed systems | |
| - Compiler/language design | |
| - Networking | |
| - AI/ML systems | |
| - Operating systems | |
| - Database internals | |
| Tiers: | |
| 0 - Scaffold (basic structure) | |
| 1 - Implement (working logic) | |
| 2 - Optimize (performance aware) | |
| 3 - Architect (system design) | |
| 4 - Frontier (novel/research level) | |
| """ | |
| import time | |
| import json | |
| from pathlib import Path | |
| CURRICULUM = { | |
| "systems": [ | |
| ("scaffold process scheduler", 0), | |
| ("implement thread pool executor", 1), | |
| ("optimize context switch handler", 2), | |
| ("architect microkernel message bus", 3), | |
| ("design capability-based security kernel",4), | |
| ], | |
| "architecture": [ | |
| ("scaffold hexagonal architecture", 0), | |
| ("implement ports and adapters pattern", 1), | |
| ("optimize dependency injection container",2), | |
| ("architect event-driven service mesh", 3), | |
| ("design self-healing distributed brain", 4), | |
| ], | |
| "programming": [ | |
| ("scaffold async task runner", 0), | |
| ("implement coroutine scheduler", 1), | |
| ("optimize hot path with caching layer", 2), | |
| ("architect reactive stream processor", 3), | |
| ("design zero-cost abstraction engine", 4), | |
| ], | |
| "frameworks": [ | |
| ("scaffold plugin system", 0), | |
| ("implement middleware pipeline", 1), | |
| ("optimize request routing table", 2), | |
| ("architect modular runtime loader", 3), | |
| ("design meta-framework with reflection", 4), | |
| ], | |
| "security": [ | |
| ("scaffold auth token validator", 0), | |
| ("implement zero-trust policy engine", 1), | |
| ("optimize cryptographic key store", 2), | |
| ("architect threat detection pipeline", 3), | |
| ("design post-quantum key exchange", 4), | |
| ], | |
| "data": [ | |
| ("scaffold schema registry", 0), | |
| ("implement columnar storage engine", 1), | |
| ("optimize query execution planner", 2), | |
| ("architect streaming data lakehouse", 3), | |
| ("design adaptive index structure", 4), | |
| ], | |
| "distributed": [ | |
| ("scaffold service registry", 0), | |
| ("implement raft consensus protocol", 1), | |
| ("optimize gossip dissemination layer", 2), | |
| ("architect byzantine fault tolerant mesh",3), | |
| ("design self-organizing peer network", 4), | |
| ], | |
| "compilers": [ | |
| ("scaffold lexer tokenizer", 0), | |
| ("implement recursive descent parser", 1), | |
| ("optimize ast transformation pass", 2), | |
| ("architect ir code generator", 3), | |
| ("design jit compilation pipeline", 4), | |
| ], | |
| "networking": [ | |
| ("scaffold tcp connection handler", 0), | |
| ("implement http/2 frame parser", 1), | |
| ("optimize packet routing table", 2), | |
| ("architect software defined network", 3), | |
| ("design congestion control algorithm", 4), | |
| ], | |
| "ml_systems": [ | |
| ("scaffold feature extraction pipeline", 0), | |
| ("implement gradient descent optimizer", 1), | |
| ("optimize inference batching layer", 2), | |
| ("architect online learning system", 3), | |
| ("design neuromorphic compute graph", 4), | |
| ], | |
| "os": [ | |
| ("scaffold virtual memory manager", 0), | |
| ("implement page replacement policy", 1), | |
| ("optimize interrupt dispatch table", 2), | |
| ("architect real-time scheduler", 3), | |
| ("design exokernel resource allocator", 4), | |
| ], | |
| "databases": [ | |
| ("scaffold btree index structure", 0), | |
| ("implement mvcc transaction engine", 1), | |
| ("optimize write-ahead log manager", 2), | |
| ("architect distributed query engine", 3), | |
| ("design learned index structure", 4), | |
| ], | |
| } | |
| DOMAINS = list(CURRICULUM.keys()) | |
| class AdaptiveCurriculum: | |
| def __init__(self): | |
| self._path = (Path.home() / ".vitalis_workspace" | |
| / "curriculum_state.json") | |
| self._cycle = 0 | |
| self._history = [] | |
| self._load() | |
| def _load(self): | |
| try: | |
| if self._path.exists(): | |
| state = json.loads(self._path.read_text()) | |
| self._cycle = state.get("cycle", 0) | |
| self._history = state.get("history", []) | |
| except Exception: | |
| pass | |
| def _save(self): | |
| try: | |
| self._path.parent.mkdir(parents=True, exist_ok=True) | |
| self._path.write_text(json.dumps({ | |
| "cycle": self._cycle, | |
| "history": self._history[-500:], | |
| })) | |
| except Exception: | |
| pass | |
| def next_task(self) -> dict: | |
| # Domain rotates every cycle across all 12 domains | |
| domain_idx = self._cycle % len(DOMAINS) | |
| domain = DOMAINS[domain_idx] | |
| # Tier advances every 12 cycles (one full domain rotation) | |
| tier = min(self._cycle // len(DOMAINS), 4) | |
| tasks = CURRICULUM[domain] | |
| task_text, _ = tasks[tier] | |
| entry = { | |
| "cycle": self._cycle, | |
| "domain": domain, | |
| "tier": tier, | |
| "task": task_text, | |
| "timestamp": time.time(), | |
| } | |
| self._history.append(entry) | |
| self._cycle += 1 | |
| if self._cycle % 10 == 0: | |
| self._save() | |
| return entry | |
| def report(self) -> dict: | |
| current_tier = min(self._cycle // len(DOMAINS), 4) | |
| tier_names = ["SCAFFOLD", "IMPLEMENT", "OPTIMIZE", | |
| "ARCHITECT", "FRONTIER"] | |
| return { | |
| "total_cycles": self._cycle, | |
| "current_tier": tier_names[current_tier], | |
| "current_domain": DOMAINS[self._cycle % len(DOMAINS)] | |
| if self._cycle > 0 else DOMAINS[0], | |
| "domains_covered": len(DOMAINS), | |
| "tasks_logged": len(self._history), | |
| } | |