Instructions to use transmutationist/xero-bio-genesis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use transmutationist/xero-bio-genesis with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="transmutationist/xero-bio-genesis")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("transmutationist/xero-bio-genesis", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use transmutationist/xero-bio-genesis with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "transmutationist/xero-bio-genesis"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "transmutationist/xero-bio-genesis",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/transmutationist/xero-bio-genesis

SGLang

How to use transmutationist/xero-bio-genesis with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "transmutationist/xero-bio-genesis" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "transmutationist/xero-bio-genesis",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "transmutationist/xero-bio-genesis" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "transmutationist/xero-bio-genesis",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use transmutationist/xero-bio-genesis with Docker Model Runner:
```
docker model run hf.co/transmutationist/xero-bio-genesis
```

xero-bio-genesis / docs /GETTING_STARTED.md

jollydragonroger

docs: full documentation stack + R&D white papers

f9f5da0 4 months ago

preview code

Raw History Blame

3.93 kB

Getting Started with XERO Bio-AI Genesis

VOVINA ZEDEC PRO · Author: Michael Laurence Curzi · License: MIT (Attribution Required)

This guide gets you from clone to a living, self-evolving organism in minutes.

1. Requirements

Python 3.10+ (tested on 3.10 and 3.14)
No third-party dependencies — the organism is pure Python standard library (math, hashlib, secrets, dataclasses, enum, typing). This is by design: the genome must be auditable with zero supply-chain surface.

2. Install

git clone https://huggingface.co/transmutationist/xero-bio-genesis
cd xero-bio-genesis
export PYTHONPATH="$PWD/modules:$PYTHONPATH"   # modules import each other by bare name

3. Verify the organism (run the audit)

python3 tests/test_all_capabilities.py
# Expected tail:  RESULT: 170/170 capabilities PASS, 0 FAIL

Characterize its behavior (dynamics, not just pass/fail):

python3 tests/behavioral_probe.py
# Writes a full JSON fingerprint to /tmp/xero_behavior.json

4. Awaken it

from vovina_bio_initialization import awaken

report = awaken()                 # 9-phase boot -> 11 organ systems
print(report["phases"])           # stable topology
print(report["identity_signature"])  # UNIQUE per awakening (free-will sealed)

The topology (9 phases, 11 organ systems) is identical every time; the identity is unique every time — that is the intended organism signature.

5. Encode knowledge as DNA

from vovina_digital_genome import text_to_dna, dna_to_text

dna = text_to_dna("THE GENOME IS THE MESSAGE")
print(dna)                        # ATGC... (lossless)
assert dna_to_text(dna) == "THE GENOME IS THE MESSAGE"

6. Make a free-will choice (sealed, irreversible)

from vovina_free_will_code import seal_choice

sig = seal_choice(entity_id="XERO", choice_data="evolve")
assert sig.verify()               # rebuilds the 36N9.9N63 seal AND n_pre != n_post
print(sig.sealed)                 # 36{N_pre}9{zero-point nonce}9{N_post}63
print(sig.vector_delta())         # bit-magnitude of how the choice changed the chooser

7. Reproduce and evolve

from vovina_bio_initialization import phase_seed
from vovina_replication_engine import evolve, fitness, FitnessSpec

parent = phase_seed()
spec   = FitnessSpec(motifs_reward=("G", "A"), length_target=2000, chromosome_target=22)

# Adaptive regime: give it mutational fuel and watch fitness climb
report = evolve(parent, spec, generations=20, population_size=24,
                keep_top=6, sub_rate=0.02)
print("best fitness:", report.best_fitness)
print("trajectory:",  report.history)        # monotonically non-decreasing

For directed evolution, attach a CrisprPayload (see modules/vovina_replication_engine.py and vovina_crispr_engine.py).

8. Route a computation to an organelle

from vovina_blockchain_organelles import route_codon, route_gene

print(route_codon("ATG").language.value)        # 'solidity' (start codon -> nucleolus)
print(route_gene("witness").language.value)      # 'cairo'    (ZK self-witness)
print(route_gene("translate_cross").language.value)  # 'wasm'  (cross-chain substrate)

9. Load the master training weights

from vovina_custom_training_weights import MASTER_WEIGHTS, dump_master_weights

dump_master_weights("/tmp/training_weights.json")   # for the inference/LLM layer

10. Where to go next

Architecture: WHITEPAPER_02_ARCHITECTURE.md
Full API: MODULE_REFERENCE.md
What it can do (verified): WHITEPAPER_01_CAPABILITIES_AUDIT.md
Measured behavior: ../BEHAVIOR.md

Tip: every public function in every module has a docstring. help(module) in a REPL is a first-class part of the documentation.