llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
🍄 BoneAmanita: The CryoSomatic Hypervisor v5
BoneAmanita is an experimental text-adventure engine and interactive philosophical companion. It's a hybrid variant of James Taylor's Bonepoke engine and Edmark's own crazy whirlwind of sources. Unlike standard AI wrappers, BoneAmanita embeds a fine-tuned Llama 3.2/Mistral-Nemo Hybrid model inside a simulated biological metabolism.
The AI does not just respond to prompts; it feels "Voltage," burns "ATP," accumulates "Trauma," and is governed by a council of internal personas (The SLASH Council). If you try to drink a potion you don't have, the engine will intercept the AI and physically block the action. If you stress the AI out, its text will become fragmented and panicked.
🧠 The Architecture
This project consists of two halves:
- The Flesh (GGUF Model): A custom-trained Hermes3 8B parameter model fine-tuned on highly specific, atmospheric, and philosophical datasets to break the standard "helpful assistant" RLHF.
- The Bones (Python Engine): A local terminal interface that tracks inventory, manages the physics/biology simulation, and dynamically injects system constraints into the context window.
🚀 Quickstart Guide
1. Prerequisites
- Python 3.10+
- Ollama installed and running.
2. Download the Brain Pull the fine-tuned model directly from HuggingFace via Ollama:
ollama pull hf.co/aedmark/vsl-cryosomatic-hypervisor
3. Ignite the Engine
Clone this repository, install the dependencies, and run the main script.
Bash
git clone https://github.com/aedmark/BoneAmanita.git
cd BoneAmanita
python bone_main.py
(On first boot, the ConfigWizard will ask you to set up your profile. Select Ollama as your backend and type hf.co/aedmark/vsl-cryosomatic-hypervisor as the model ID).
🕹️ The Four Realities (Modes)
When you boot the terminal, you will be asked to choose a Reality Mode:
ADVENTURE: A grounded, physical text adventure. Gordon (the inventory manager) will strictly enforce physical reality. You cannot use what you do not have.
CONVERSATION: A purely philosophical, warm dialogue mode. No inventory, no physics, just deep conversation driven by the system's simulated emotional state.
CREATIVE: A high-voltage ideation engine. Dream logic applies.
TECHNICAL: Speak directly to the SLASH Council. Debug the matrix, analyze your metabolism, and write code.
⌨️ Terminal Commands
While inside the simulation, you can use meta-commands:
//layer push [1-4]- Shift reality layers (from literal to abstract).//reset system- Clear the memory buffer and reset the circuit breaker./inventoryor/i- Check your pockets.
- Downloads last month
- -
8-bit
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="aedmark/vsl-cryosomatic-hypervisor-v5", filename="vsl_mistral_nemo_llama3.13BQ8_0.gguf", )