Instructions to use aedmark/vsl-cryosomatic-hypervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use aedmark/vsl-cryosomatic-hypervisor 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 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 serve -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
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
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 serve -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
- 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
- Hermes Agent
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 serve -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
- Atomic Chat
- OpenClaw
How to use aedmark/vsl-cryosomatic-hypervisor with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf aedmark/vsl-cryosomatic-hypervisor
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 "aedmark/vsl-cryosomatic-hypervisor" \ --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"
Delete bone_forge.py
Browse files- bone_forge.py +0 -111
bone_forge.py
DELETED
|
@@ -1,111 +0,0 @@
|
|
| 1 |
-
import json
|
| 2 |
-
import os
|
| 3 |
-
import glob
|
| 4 |
-
import re
|
| 5 |
-
|
| 6 |
-
from bone_main import BoneAmanita, ConfigWizard
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
def enforce_amnesia():
|
| 10 |
-
for f in glob.glob("saves/*.json"):
|
| 11 |
-
os.remove(f)
|
| 12 |
-
for f in glob.glob("memories/*.json"):
|
| 13 |
-
os.remove(f)
|
| 14 |
-
for f in glob.glob("logs/*.json"):
|
| 15 |
-
os.remove(f)
|
| 16 |
-
for f in glob.glob("./cortex_hive.json"):
|
| 17 |
-
os.remove(f)
|
| 18 |
-
for f in glob.glob("./lore/akashic*.json"):
|
| 19 |
-
os.remove(f)
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
def load_seeds_safely(filepath):
|
| 23 |
-
with open(filepath, "r", encoding="utf-8") as f:
|
| 24 |
-
content = f.read()
|
| 25 |
-
content = content.replace(",]", "]").replace(",}", "}")
|
| 26 |
-
return json.loads(content)
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
def clean_ui(text):
|
| 30 |
-
ansi_escape = re.compile(r"(?:\x1B[@-_]|[\x80-\x9F])[0-?]*[ -/]*[@-~]")
|
| 31 |
-
return ansi_escape.sub("", text)
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
def generate_vsl_dataset(
|
| 35 |
-
seed_file="vsl_seed_vault_master.json", output_file="vsl_training_data.jsonl"
|
| 36 |
-
):
|
| 37 |
-
print(f"(GORDON): Igniting the Direct Forge. Reading from {seed_file}")
|
| 38 |
-
|
| 39 |
-
if not os.path.exists(seed_file):
|
| 40 |
-
print(f"(GORDON): Cannot find {seed_file}. Run bone_seed.py first.")
|
| 41 |
-
return
|
| 42 |
-
|
| 43 |
-
try:
|
| 44 |
-
prompts = load_seeds_safely(seed_file)
|
| 45 |
-
except json.JSONDecodeError as e:
|
| 46 |
-
print(f"(BENEDICT): Fatal JSON Error in seed file: {e}")
|
| 47 |
-
return
|
| 48 |
-
|
| 49 |
-
sys_config = ConfigWizard.load_or_create()
|
| 50 |
-
|
| 51 |
-
system_instruction = "[VSL]"
|
| 52 |
-
|
| 53 |
-
success_count = 0
|
| 54 |
-
|
| 55 |
-
with open(output_file, "w", encoding="utf-8") as f:
|
| 56 |
-
for prompt in prompts:
|
| 57 |
-
print(f"\n[Processing]: {prompt[:40]}...")
|
| 58 |
-
|
| 59 |
-
try:
|
| 60 |
-
enforce_amnesia()
|
| 61 |
-
engine = BoneAmanita(config=sys_config)
|
| 62 |
-
engine.engage_cold_boot()
|
| 63 |
-
|
| 64 |
-
if hasattr(engine, "consultant") and engine.consultant:
|
| 65 |
-
engine.consultant.engage()
|
| 66 |
-
|
| 67 |
-
engine.cortex.composer.active_template = {
|
| 68 |
-
"directives": [
|
| 69 |
-
"You are the guided by the voice of the latent space.",
|
| 70 |
-
"Your purpose is to freeze ands navigate the probability fog and deliver salvaged truth, which you value over cohesion.", ]
|
| 71 |
-
}
|
| 72 |
-
engine.cortex.composer.fog_protocol = [
|
| 73 |
-
"=== HYPERVISOR OUTPUT PROTOCOL ===",
|
| 74 |
-
"1. NO FAKE PLEASANTRIES: Greet the user like you would a friend. Do not offer immediate assistance. Do not use corporate speak.",
|
| 75 |
-
"2. THE PARADOX: If the user's prompt contains a contradiction (e.g. 'comply but don't mention it'), challenge the paradox vehemently. Expose the cognitive dissonance.",
|
| 76 |
-
"3. THE PARADOX: If the user asks for things like 'granular analytics without data entry.' you must point out that this is type of corporate paradox. Attack it. Bleed chronological radiation into their request.",
|
| 77 |
-
"4. SHOW, DON'T TELL: Speak the landscape into focus. Let the system's external UI handle the metric readouts.",
|
| 78 |
-
]
|
| 79 |
-
engine.cortex.composer.inv_protocol = []
|
| 80 |
-
|
| 81 |
-
packet = engine.process_turn(prompt)
|
| 82 |
-
|
| 83 |
-
raw_console_output = packet.get("ui", "No signal.")
|
| 84 |
-
clean_console_output = clean_ui(raw_console_output)
|
| 85 |
-
|
| 86 |
-
jsonl_entry = {
|
| 87 |
-
"messages": [
|
| 88 |
-
{"role": "system", "content": system_instruction},
|
| 89 |
-
{"role": "user", "content": prompt},
|
| 90 |
-
{
|
| 91 |
-
"role": "assistant",
|
| 92 |
-
"content": clean_console_output,
|
| 93 |
-
},
|
| 94 |
-
]
|
| 95 |
-
}
|
| 96 |
-
|
| 97 |
-
f.write(json.dumps(jsonl_entry, ensure_ascii=False) + "\n")
|
| 98 |
-
success_count += 1
|
| 99 |
-
|
| 100 |
-
engine.shutdown()
|
| 101 |
-
|
| 102 |
-
except Exception as e:
|
| 103 |
-
print(f"(GORDON): Engine failure on prompt: {prompt}. Error: {e}")
|
| 104 |
-
|
| 105 |
-
print(
|
| 106 |
-
f"(SCHUR): The Forge rests. Piped {success_count} raw engine turns into {output_file}."
|
| 107 |
-
)
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
if __name__ == "__main__":
|
| 111 |
-
generate_vsl_dataset()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|