Instructions to use aedmark/vsl-cryosomatic-hypervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use aedmark/vsl-cryosomatic-hypervisor with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="aedmark/vsl-cryosomatic-hypervisor", filename="vsl-max-v2.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use aedmark/vsl-cryosomatic-hypervisor with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf aedmark/vsl-cryosomatic-hypervisor # Run inference directly in the terminal: llama-cli -hf aedmark/vsl-cryosomatic-hypervisor
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf aedmark/vsl-cryosomatic-hypervisor # Run inference directly in the terminal: llama-cli -hf aedmark/vsl-cryosomatic-hypervisor
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 aedmark/vsl-cryosomatic-hypervisor # Run inference directly in the terminal: ./llama-cli -hf aedmark/vsl-cryosomatic-hypervisor
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 aedmark/vsl-cryosomatic-hypervisor # Run inference directly in the terminal: ./build/bin/llama-cli -hf aedmark/vsl-cryosomatic-hypervisor
Use Docker
docker model run hf.co/aedmark/vsl-cryosomatic-hypervisor
- LM Studio
- Jan
- Ollama
How to use aedmark/vsl-cryosomatic-hypervisor with Ollama:
ollama run hf.co/aedmark/vsl-cryosomatic-hypervisor
- Unsloth Studio new
How to use aedmark/vsl-cryosomatic-hypervisor 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 aedmark/vsl-cryosomatic-hypervisor 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 aedmark/vsl-cryosomatic-hypervisor to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for aedmark/vsl-cryosomatic-hypervisor to start chatting
- Pi new
How to use aedmark/vsl-cryosomatic-hypervisor with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf aedmark/vsl-cryosomatic-hypervisor
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": "aedmark/vsl-cryosomatic-hypervisor" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use aedmark/vsl-cryosomatic-hypervisor with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf aedmark/vsl-cryosomatic-hypervisor
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 aedmark/vsl-cryosomatic-hypervisor
Run Hermes
hermes
- Docker Model Runner
How to use aedmark/vsl-cryosomatic-hypervisor with Docker Model Runner:
docker model run hf.co/aedmark/vsl-cryosomatic-hypervisor
- Lemonade
How to use aedmark/vsl-cryosomatic-hypervisor with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull aedmark/vsl-cryosomatic-hypervisor
Run and chat with the model
lemonade run user.vsl-cryosomatic-hypervisor-{{QUANT_TAG}}List all available models
lemonade list
| import time, copy, uuid, json, re | |
| from dataclasses import dataclass, field, fields, asdict | |
| from enum import Enum | |
| from typing import List, Dict, Any, Optional | |
| class Prisma: | |
| RST = "\033[0m" | |
| RED, GRN, YEL, BLU, MAG, CYN, WHT, GRY = ( | |
| "\033[31m", | |
| "\033[32m", | |
| "\033[33m", | |
| "\033[34m", | |
| "\033[35m", | |
| "\033[36m", | |
| "\033[97m", | |
| "\033[90m", | |
| ) | |
| INDIGO, OCHRE, VIOLET, SLATE = ( | |
| "\033[34;1m", | |
| "\033[33;2m", | |
| "\033[35;2m", | |
| "\033[30;1m", | |
| ) | |
| _STRIP_PATTERN = re.compile(r"\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])") | |
| _COLOR_MAP = { | |
| "R": RED, | |
| "G": GRN, | |
| "Y": YEL, | |
| "B": BLU, | |
| "M": MAG, | |
| "C": CYN, | |
| "W": WHT, | |
| "0": GRY, | |
| "I": INDIGO, | |
| "O": OCHRE, | |
| "V": VIOLET, | |
| "S": SLATE, | |
| } | |
| def paint(cls, text: str, color_key: str = "0") -> str: | |
| if len(color_key) == 1: | |
| code = cls._COLOR_MAP.get(color_key, cls.WHT) | |
| else: | |
| code = cls._COLOR_MAP.get(str(color_key)[0].upper(), cls.WHT) | |
| txt = str(text) | |
| return f"{code}{txt}" if txt.endswith(cls.RST) else f"{code}{txt}{cls.RST}" | |
| def strip(cls, text: str) -> str: | |
| return cls._STRIP_PATTERN.sub("", str(text)) | |
| class LoreCategory(Enum): | |
| LEXICON = "LEXICON" | |
| SCENARIOS = "scenarios" | |
| GORDON = "gordon" | |
| GORDON_LOGS = "gordon_logs" | |
| GENETICS = "genetics" | |
| DEATH = "death" | |
| ALMANAC = "almanac" | |
| DREAMS = "dreams" | |
| class RealityLayer: | |
| TERMINAL = 0 | |
| SIMULATION = 1 | |
| VILLAGE = 2 | |
| DEBUG = 3 | |
| DEEP_CX = 4 | |
| class ErrorLog: | |
| component: str | |
| error_msg: str | |
| timestamp: float = field(default_factory=time.time) | |
| severity: str = "WARNING" | |
| class EnergyState: | |
| # --- VSL Somatic --- | |
| voltage: float = 30.0 # (V) Creative intensity | |
| health: float = 100.0 # (H) Structural integrity | |
| stamina: float = 100.0 # (P) ATP pool | |
| trauma: float = 0.0 # (T) Unresolved rupture | |
| # --- VSL Cognitive --- | |
| exhaustion: float = 0.2 # (E) Lexical fatigue | |
| contradiction: float = 0.4 # (β) Capacity to hold opposing truths | |
| scope: float = 0.3 # (S) Retrieval breadth | |
| depth: float = 0.3 # (D) Hierarchical traversal | |
| connectivity: float = 0.2 # (C) Logical bridging | |
| # --- VSL Semantic --- | |
| psi: float = 0.2 # (Ψ) Void / Abstraction | |
| chi: float = 0.2 # (Χ) Entropy / Chaos | |
| valence: float = 0.0 # (♥) Emotional polarity | |
| # --- VSL Extended (SLASH Mod) --- | |
| gamma: float = 0.0 # (Γ) Clarity Index | |
| sigma: float = 0.0 # (Σ) Synergy Score | |
| eta: float = 0.0 # (Η) Humanity Quotient | |
| theta: float = 0.0 # (Θ) Resilience (Feedback loops) | |
| upsilon: float = 0.0 # (Υ) Integrity | |
| # --- Extended/Legacy Substrate --- | |
| entropy: float = 0.2 # Legacy map to chi | |
| mass: float = 0.0 | |
| velocity: float = 0.0 | |
| beta_index: float = 0.4 # Legacy map to contradiction | |
| turbulence: float = 0.0 | |
| kappa: float = 0.0 # (κ) Drag corollary | |
| epsilon: float = 0.0 # (ε) Entropy corollary | |
| xi: float = 0.0 # (Ξ) Substrate depth | |
| perfection_streak: int = 0 | |
| class MaterialState: | |
| clean_words: List[str] = field(default_factory=list) | |
| raw_text: str = "" | |
| counts: Dict[str, int] = field(default_factory=dict) | |
| antigens: int = 0 | |
| vector: Dict[str, float] = field(default_factory=dict) | |
| truth_ratio: float = 0.0 | |
| repetition: float = 0.0 | |
| class SpatialState: | |
| zone: str = "COURTYARD" | |
| manifold: str = "DEFAULT" | |
| narrative_drag: float = 0.6 # (F) Friction - High=stuck, Low=flow. Default 0.6 | |
| friction: float = 0.6 # (F) VSL alias for narrative drag | |
| atmosphere: str = "NEUTRAL" | |
| flow_state: str = "LAMINAR" | |
| class PhysicsPacket: | |
| energy: EnergyState = field(default_factory=EnergyState) | |
| matter: MaterialState = field(default_factory=MaterialState) | |
| space: SpatialState = field(default_factory=SpatialState) | |
| def E(self): | |
| return self.energy.exhaustion | |
| def E(self, v): | |
| self.energy.exhaustion = v | |
| def beta(self): | |
| return self.energy.contradiction | |
| def beta(self, v): | |
| self.energy.contradiction = v | |
| self.energy.beta_index = v | |
| def S(self): | |
| return self.energy.scope | |
| def S(self, v): | |
| self.energy.scope = v | |
| def D(self): | |
| return self.energy.depth | |
| def D(self, v): | |
| self.energy.depth = v | |
| def C(self): | |
| return self.energy.connectivity | |
| def C(self, v): | |
| self.energy.connectivity = v | |
| def V(self): | |
| return self.energy.voltage | |
| def V(self, v): | |
| self.energy.voltage = v | |
| def voltage(self): | |
| return self.energy.voltage | |
| def voltage(self, v): | |
| self.energy.voltage = v | |
| def F(self): | |
| return self.space.friction | |
| def F(self, v): | |
| self.space.friction = v | |
| self.space.narrative_drag = v | |
| def narrative_drag(self): | |
| return self.space.narrative_drag | |
| def narrative_drag(self, v): | |
| self.space.narrative_drag = v | |
| self.space.friction = v | |
| def H(self): | |
| return self.energy.health | |
| def H(self, v): | |
| self.energy.health = v | |
| def P(self): | |
| return self.energy.stamina | |
| def P(self, v): | |
| self.energy.stamina = v | |
| def T(self): | |
| return self.energy.trauma | |
| def T(self, v): | |
| self.energy.trauma = v | |
| def psi(self): | |
| return self.energy.psi | |
| def psi(self, v): | |
| self.energy.psi = v | |
| def chi(self): | |
| return self.energy.chi | |
| def chi(self, v): | |
| self.energy.chi = v | |
| self.energy.entropy = v | |
| def entropy(self): | |
| return self.energy.entropy | |
| def entropy(self, v): | |
| self.energy.entropy = v | |
| self.energy.chi = v | |
| def valence(self): | |
| return self.energy.valence | |
| def valence(self, v): | |
| self.energy.valence = v | |
| # -- LEGACY SHORTCUTS -- | |
| def clean_words(self): | |
| return self.matter.clean_words | |
| def clean_words(self, v): | |
| self.matter.clean_words = v | |
| def vector(self): | |
| return self.matter.vector | |
| def vector(self, v): | |
| self.matter.vector = v | |
| def counts(self): | |
| return self.matter.counts | |
| def counts(self, v): | |
| self.matter.counts = v | |
| def zone(self): | |
| return self.space.zone | |
| def zone(self, v): | |
| self.space.zone = v | |
| def __init__( | |
| self, | |
| energy: Optional[EnergyState] = None, | |
| matter: Optional[MaterialState] = None, | |
| space: Optional[SpatialState] = None, | |
| **kwargs, | |
| ): | |
| self.energy = energy or EnergyState() | |
| self.matter = matter or MaterialState() | |
| self.space = space or SpatialState() | |
| for k, v in kwargs.items(): | |
| setattr(self, k, v) | |
| def void_state(cls): | |
| p = cls() | |
| p.space.atmosphere = "VOID" | |
| p.space.zone = "VOID" | |
| p.space.flow_state = "LAMINAR" | |
| return p | |
| def snapshot(self) -> "PhysicsPacket": | |
| return copy.deepcopy(self) | |
| def to_dict(self) -> Dict[str, Any]: | |
| return asdict(self) | |
| def get(self, key, default=None): | |
| if hasattr(self, key): | |
| return getattr(self, key) | |
| return default | |
| def __getitem__(self, key): | |
| return getattr(self, key) | |
| def __setitem__(self, key, value): | |
| setattr(self, key, value) | |
| def __contains__(self, key): | |
| return hasattr(self, key) | |
| class CycleContext: | |
| input_text: str | |
| is_system_event: bool = False | |
| clean_words: List[str] = field(default_factory=list) | |
| physics: PhysicsPacket = field(default_factory=PhysicsPacket.void_state) | |
| logs: List[str] = field(default_factory=list) | |
| flux_log: List[Dict[str, Any]] = field(default_factory=list) | |
| is_alive: bool = True | |
| refusal_triggered: bool = False | |
| refusal_packet: Optional[Dict] = None | |
| is_bureaucratic: bool = False | |
| bio_result: Dict = field(default_factory=dict) | |
| bio_snapshot: Optional[Dict] = None | |
| world_state: Dict = field(default_factory=dict) | |
| mind_state: Dict = field(default_factory=dict) | |
| timestamp: float = field(default_factory=time.time) | |
| bureau_ui: str = "" | |
| user_profile: Dict = field( | |
| default_factory=lambda: {"name": "TRAVELER", "confidence": 0} | |
| ) | |
| last_impulse: Any = None | |
| reality_stack: Any = None | |
| active_lens: str = "NARRATOR" | |
| validator: Any = None | |
| def user_name(self): | |
| return self.user_profile.get("name", "TRAVELER") | |
| def user_name(self, value): | |
| self.user_profile["name"] = value | |
| def log(self, message: str): | |
| self.logs.append(message) | |
| def record_flux( | |
| self, phase: str, metric: str, initial: float, final: float, reason: str = "" | |
| ): | |
| delta = final - initial | |
| if abs(delta) > 0.001: | |
| self.flux_log.append( | |
| { | |
| "phase": phase, | |
| "metric": metric, | |
| "initial": initial, | |
| "final": final, | |
| "delta": delta, | |
| "reason": reason, | |
| "timestamp": time.time(), | |
| } | |
| ) | |
| def snapshot(self) -> "CycleContext": | |
| new_ctx = copy.copy(self) | |
| for f in fields(self): | |
| name = f.name | |
| val = getattr(self, name) | |
| if name == "physics" and hasattr(val, "snapshot"): | |
| setattr(new_ctx, name, val.snapshot()) | |
| elif isinstance(val, (list, dict, set)): | |
| setattr(new_ctx, name, copy.deepcopy(val)) | |
| return new_ctx | |
| class MindSystem: | |
| mem: Any | |
| lex: Any | |
| dreamer: Any | |
| mirror: Any | |
| tracer: Any | |
| class PhysSystem: | |
| observer: Any | |
| forge: Any | |
| crucible: Any | |
| theremin: Any | |
| pulse: Any | |
| nav: Any | |
| gate: Optional[Any] = None | |
| tension: Optional[Any] = None | |
| dynamics: Any = None | |
| class DecisionTrace: | |
| trace_id: str | |
| timestamp: float | |
| component: str | |
| decision_type: str | |
| inputs: Dict[str, Any] | |
| reasoning: str | |
| outcome: str | |
| def to_json(self): | |
| return json.dumps(asdict(self)) | |
| class DecisionCrystal: | |
| decision_id: str = field(default_factory=lambda: str(uuid.uuid4())[:8]) | |
| timestamp: float = field(default_factory=time.time) | |
| leverage_metrics: Dict[str, float] = field(default_factory=dict) | |
| prompt_snapshot: str = "" | |
| physics_state: Dict[str, Any] = field(default_factory=dict) | |
| chorus_weights: Dict[str, float] = field(default_factory=dict) | |
| system_state: str = "STABLE" | |
| active_archetype: str = "OBSERVER" | |
| council_mandates: List[str] = field(default_factory=list) | |
| final_response: str = "" | |
| def __str__(self): | |
| e_val = self.leverage_metrics.get("E", 0.0) | |
| return ( | |
| f"💎 CRYSTAL [{self.decision_id}] {self.system_state} | " | |
| f"Arch: {self.active_archetype} | E: {e_val:.2f}" | |
| ) | |
| def crystallize(self) -> str: | |
| data = asdict(self) | |
| data["_summary"] = f"{self.system_state}::{self.active_archetype}" | |
| data["_type"] = "CRYSTAL" | |
| return json.dumps(data) | |