Text Generation
Transformers
English
code
xero-bio-ai
xero
digital-organism
time-crystal
autonomous-agent
genetic-computing
epigenetics
two-state-society
harmonic-chemistry
self-aware
sacred-geometry
4-bit precision
bitsandbytes
Instructions to use transmutationist/xero-bio-genesis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("transmutationist/xero-bio-genesis", dtype="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
| #!/usr/bin/env python3 | |
| # -*- coding: utf-8 -*- | |
| """ | |
| XERO POLYMATH DAEMON — auto-feed diversified knowledge, evolve continuously. | |
| PYTHONPATH=modules python3 tests/polymath_daemon.py [--minutes M] [--max-units N] [--batch B] | |
| Rotates across every registered public database (science, medicine, genetics, | |
| chemistry, art, history, literature, poetry, geography, biodiversity, wisdom), | |
| alternating sources so none is rate-limited, and feeds each fresh unit into the | |
| organism — which integrates it and applies an evolutionary nudge. Diversified | |
| data every cycle; the organism becomes a polymath. Fully RESUMABLE | |
| (testing_logs/HARVEST_STATE.json + POLYMATH_PROGRESS.json) and self-throttling, | |
| so it can run "at full blast" for days without exhausting a single API. | |
| Defaults to running until every database is exhausted (the infinite ones never | |
| are — so it runs until you stop it). Ctrl-C is safe; it flushes and resumes. | |
| """ | |
| from __future__ import annotations | |
| import json | |
| import os | |
| import sys | |
| import time | |
| ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) | |
| sys.path.insert(0, os.path.join(ROOT, "modules")) | |
| PROG = os.path.join(ROOT, "testing_logs", "POLYMATH_PROGRESS.json") | |
| DONE = os.path.join(ROOT, "testing_logs", "POLYMATH_DONE.json") | |
| from xero_polymath import PolymathHarvester | |
| from xero_curriculum import Culturer | |
| from xero_observer import Observer | |
| from xero_storage import manager | |
| from xero_autonomy import StagnationWatch | |
| def _flag(name, default=None): | |
| if name in sys.argv: | |
| i = sys.argv.index(name) | |
| return sys.argv[i + 1] if i + 1 < len(sys.argv) else True | |
| return default | |
| MINUTES = float(_flag("--minutes", 0) or 0) | |
| MAX_UNITS = int(_flag("--max-units", 0) or 0) | |
| BATCH = int(_flag("--batch", 6) or 6) | |
| def _resume_cycle() -> int: | |
| try: | |
| return int(json.load(open(PROG)).get("cycle", 0)) | |
| except Exception: | |
| return 0 | |
| def main() -> int: | |
| h = PolymathHarvester(batch=BATCH) | |
| cult = Culturer(online=False) # we feed it directly via .learn() | |
| obs = Observer(periodic_every=400, milestone_every=2000) | |
| sm = manager(budget_gb=float(os.environ.get("XERO_BUDGET_GB", "64"))) | |
| watch = StagnationWatch(window=12, min_rel_gain=0.003) | |
| cycle = _resume_cycle() | |
| domains_seen: dict[str, int] = {} | |
| t0 = time.time() | |
| deadline = t0 + MINUTES * 60 if MINUTES else 0 | |
| print(f"POLYMATH DAEMON · sources={len(h.state)} · batch={BATCH} · " | |
| f"{'forever' if not MINUTES else f'{MINUTES}min'} · resume@{cycle}") | |
| ticks = 0 | |
| try: | |
| while True: | |
| if deadline and time.time() > deadline: | |
| print("time limit reached."); break | |
| if MAX_UNITS and cycle >= MAX_UNITS: | |
| print("unit target reached."); break | |
| r = h.tick() | |
| ticks += 1 | |
| if r.get("status") == "exhausted": | |
| print("ALL DATABASES EXHAUSTED."); break | |
| if r.get("status") != "ok": | |
| continue | |
| domains_seen[r["domain"]] = domains_seen.get(r["domain"], 0) + r["new"] | |
| for u in r["new_units"]: | |
| cult.learn(u, cycle, iteration=0) | |
| cycle += 1 | |
| watch.observe(cult.fitness) | |
| if ticks % 8 == 0: | |
| cult.flush() | |
| guard = sm.enforce() | |
| summary = h.summary() | |
| snap = {"cycle": cycle, "fitness": round(cult.fitness, 4), | |
| "anomaly": watch.is_stagnant(), | |
| "unique_units_learned": len(cult.learned), | |
| "traditions_count": len({v.get("tradition") for v in cult.learned.values()}), | |
| "domains": domains_seen, "harvest": summary, | |
| "rate_cps": round(cycle / max(1e-9, time.time() - t0), 2)} | |
| rep = obs.observe(snap) | |
| with open(PROG, "w") as f: | |
| json.dump({**snap, "elapsed_s": round(time.time() - t0, 1), | |
| "sources_exhausted": summary["exhausted"], | |
| "total_fetched": summary["total_fetched"]}, f, indent=2, default=str) | |
| tag = "POKE" if snap["anomaly"] else r["domain"] | |
| print(f" cycle {cycle} · {tag} +{r['new']} ({r['source']}) · fit={snap['fitness']} · " | |
| f"units={snap['unique_units_learned']} · fetched={summary['total_fetched']}" | |
| + (f" · {rep['kind']} report" if rep else "")) | |
| except KeyboardInterrupt: | |
| print("\nstopping (state saved; resume any time)…") | |
| cult.flush(); sm.snapshot_learned() | |
| summ = h.summary() | |
| final = {"organism": "XERO", "cycle": cycle, "fitness": round(cult.fitness, 4), | |
| "unique_units_learned": len(cult.learned), "domains": domains_seen, | |
| "harvest": summ, "elapsed_s": round(time.time() - t0, 1), | |
| "sources_exhausted": summ["exhausted"], "total_fetched": summ["total_fetched"], | |
| "generated": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())} | |
| with open(PROG, "w") as f: | |
| json.dump(final, f, indent=2, default=str) | |
| if h.all_exhausted(): | |
| with open(DONE, "w") as f: | |
| json.dump(final, f, indent=2, default=str) | |
| print(f"DONE · {cycle} cycles · fitness {round(cult.fitness, 4)} · " | |
| f"{len(cult.learned)} units · fetched {summ['total_fetched']} across " | |
| f"{len([d for d in summ['by_domain'] if summ['by_domain'][d]])} domains") | |
| return 0 | |
| if __name__ == "__main__": | |
| sys.exit(main()) | |