Text Generation
PyTorch
GGUF
English
quantum
quantum-entropy
from-scratch
char-level
cosmic-synapse-theory
custom-architecture
llama-cpp
continual-learning
reproducible-seed
open-science
null-results
Instructions to use phera-ra/QC67_cosmo 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 phera-ra/QC67_cosmo 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 phera-ra/QC67_cosmo # Run inference directly in the terminal: llama cli -hf phera-ra/QC67_cosmo
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf phera-ra/QC67_cosmo # Run inference directly in the terminal: llama cli -hf phera-ra/QC67_cosmo
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 phera-ra/QC67_cosmo # Run inference directly in the terminal: ./llama-cli -hf phera-ra/QC67_cosmo
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 phera-ra/QC67_cosmo # Run inference directly in the terminal: ./build/bin/llama-cli -hf phera-ra/QC67_cosmo
Use Docker
docker model run hf.co/phera-ra/QC67_cosmo
- LM Studio
- Jan
- vLLM
How to use phera-ra/QC67_cosmo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "phera-ra/QC67_cosmo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "phera-ra/QC67_cosmo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/phera-ra/QC67_cosmo
- Ollama
How to use phera-ra/QC67_cosmo with Ollama:
ollama run hf.co/phera-ra/QC67_cosmo
- Unsloth Studio
How to use phera-ra/QC67_cosmo 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 phera-ra/QC67_cosmo 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 phera-ra/QC67_cosmo to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for phera-ra/QC67_cosmo to start chatting
- Docker Model Runner
How to use phera-ra/QC67_cosmo with Docker Model Runner:
docker model run hf.co/phera-ra/QC67_cosmo
- Lemonade
How to use phera-ra/QC67_cosmo with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull phera-ra/QC67_cosmo
Run and chat with the model
lemonade run user.QC67_cosmo-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
| #!/usr/bin/env python3 | |
| """ | |
| Persistent continual 54D learning loop. | |
| Watches Cosmos/data/cosmos/experience_corpus.txt and runs one bounded CPU | |
| training burst only after enough genuinely new lines arrive. The last trained | |
| line count survives restarts, a process lock prevents duplicate learners, and a | |
| parent/stop-file contract lets WAKE_HER shut the learner down with Cosmos. | |
| """ | |
| from __future__ import annotations | |
| import json | |
| import os | |
| from pathlib import Path | |
| import subprocess | |
| import sys | |
| import time | |
| PR = Path(__file__).resolve().parents[1] | |
| CORPUS = PR / "Cosmos" / "data" / "cosmos" / "experience_corpus.txt" | |
| TRAINER = PR / "scripts" / "train_cosmos_from_play.py" | |
| CHECKPOINT = PR / "Cosmos" / "checkpoints" / "cosmos" / "cosmos_play.pt" | |
| STATE = PR / "Cosmos" / "checkpoints" / "cosmos" / "cosmos_54d_loop_state.json" | |
| LOCK = PR / "Cosmos" / "checkpoints" / "cosmos" / "cosmos_54d_loop.lock" | |
| INTERVAL = max(30, int(os.getenv("COSMOS_54D_TRAIN_INTERVAL_S", "1800"))) | |
| MIN_NEW = max(1, int(os.getenv("COSMOS_54D_TRAIN_MIN_NEW", "12"))) | |
| START_DELAY = max(0, int(os.getenv("COSMOS_54D_TRAIN_START_DELAY_S", "0"))) | |
| PARENT_PID = int(os.getenv("COSMOS_54D_PARENT_PID", "0") or 0) | |
| STOP_FILE = Path(os.getenv("COSMOS_54D_STOP_FILE", "")) if os.getenv("COSMOS_54D_STOP_FILE") else None | |
| def _say(message: str) -> None: | |
| print(f"[54D-LOOP] {message}", flush=True) | |
| def _lines() -> int: | |
| try: | |
| with CORPUS.open("r", encoding="utf-8", errors="ignore") as handle: | |
| return sum(1 for _ in handle) | |
| except Exception: | |
| return 0 | |
| def _parent_alive() -> bool: | |
| """Return whether the wake process still exists on every supported OS. | |
| ``os.kill(pid, 0)`` is not a reliable Windows existence probe: on some | |
| Python builds it raises ``SystemError``/WinError 87 even for a live PID. | |
| Use a real process handle on Windows, then retain the POSIX probe elsewhere. | |
| """ | |
| if PARENT_PID <= 0: | |
| return True | |
| if os.name == "nt": | |
| try: | |
| import ctypes | |
| access = 0x00100000 | 0x00001000 # SYNCHRONIZE | QUERY_LIMITED_INFORMATION | |
| handle = ctypes.windll.kernel32.OpenProcess(access, False, PARENT_PID) | |
| if handle: | |
| ctypes.windll.kernel32.CloseHandle(handle) | |
| return True | |
| return False | |
| except Exception: | |
| # A probe failure must never crash the learner. The stop file is | |
| # still authoritative when WAKE_HER shuts down. | |
| return True | |
| try: | |
| os.kill(PARENT_PID, 0) | |
| return True | |
| except (OSError, SystemError, ValueError): | |
| return False | |
| def _stopping() -> bool: | |
| return bool((STOP_FILE and STOP_FILE.exists()) or not _parent_alive()) | |
| def _sleep(seconds: int) -> bool: | |
| deadline = time.monotonic() + max(0, seconds) | |
| while time.monotonic() < deadline: | |
| if _stopping(): | |
| return False | |
| time.sleep(min(2.0, max(0.0, deadline - time.monotonic()))) | |
| return not _stopping() | |
| def _single_instance(): | |
| LOCK.parent.mkdir(parents=True, exist_ok=True) | |
| handle = LOCK.open("a+b") | |
| handle.seek(0, os.SEEK_END) | |
| if handle.tell() == 0: | |
| handle.write(b"0") | |
| handle.flush() | |
| handle.seek(0) | |
| try: | |
| if os.name == "nt": | |
| import msvcrt | |
| msvcrt.locking(handle.fileno(), msvcrt.LK_NBLCK, 1) | |
| else: | |
| import fcntl | |
| fcntl.flock(handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB) | |
| except (OSError, IOError): | |
| handle.close() | |
| return None | |
| return handle | |
| def _load_last_trained(current_lines: int) -> int: | |
| try: | |
| value = json.loads(STATE.read_text(encoding="utf-8")) | |
| return max(0, int(value.get("last_trained_lines", 0))) | |
| except Exception: | |
| pass | |
| # Migrate safely: if the checkpoint is newer than the corpus, it already | |
| # represents the current data. Otherwise the accumulated new corpus is due. | |
| try: | |
| if CHECKPOINT.is_file() and CHECKPOINT.stat().st_mtime_ns >= CORPUS.stat().st_mtime_ns: | |
| return current_lines | |
| except Exception: | |
| pass | |
| return 0 | |
| def _save_state(lines: int) -> None: | |
| STATE.parent.mkdir(parents=True, exist_ok=True) | |
| value = { | |
| "schema": "cosmos.54d_continual_state.v1", | |
| "last_trained_lines": int(lines), | |
| "checkpoint": str(CHECKPOINT), | |
| "checkpoint_mtime_ns": CHECKPOINT.stat().st_mtime_ns if CHECKPOINT.is_file() else None, | |
| "updated_at": time.time(), | |
| } | |
| temp = STATE.with_name(f"{STATE.name}.tmp.{os.getpid()}") | |
| temp.write_text(json.dumps(value, indent=2) + "\n", encoding="utf-8") | |
| os.replace(temp, STATE) | |
| def _mem_too_high() -> bool: | |
| try: | |
| import psutil | |
| vm = psutil.virtual_memory() | |
| return vm.percent >= 90.0 or vm.available < 1_500_000_000 | |
| except Exception: | |
| return False | |
| def _run_burst() -> tuple[int | None, str]: | |
| env = dict(os.environ) | |
| env.setdefault("COSMOS_PLAY_TRAIN_STEPS", "120") | |
| env.setdefault("COSMOS_PLAY_TRAIN_SEC", "360") | |
| env.setdefault("COSMOS_PLAY_TRAIN_THREADS", "2") | |
| env.setdefault("PYTHONIOENCODING", "utf-8") | |
| proc = subprocess.Popen( | |
| [sys.executable, str(TRAINER)], | |
| env=env, | |
| stdout=subprocess.PIPE, | |
| stderr=subprocess.STDOUT, | |
| text=True, | |
| encoding="utf-8", | |
| errors="replace", | |
| ) | |
| deadline = time.monotonic() + 900 | |
| while proc.poll() is None: | |
| if _stopping(): | |
| proc.terminate() | |
| try: | |
| proc.wait(timeout=10) | |
| except Exception: | |
| proc.kill() | |
| output, _ = proc.communicate() | |
| return None, output or "" | |
| if time.monotonic() >= deadline: | |
| proc.kill() | |
| output, _ = proc.communicate() | |
| return -1, (output or "") + "\ntrainer timeout" | |
| time.sleep(1) | |
| output, _ = proc.communicate() | |
| return proc.returncode, output or "" | |
| def main() -> int: | |
| lock_handle = _single_instance() | |
| if lock_handle is None: | |
| _say("another continual learner already owns the lock; this copy exits") | |
| return 0 | |
| try: | |
| _say( | |
| f"armed: {MIN_NEW}+ new lines, check every {INTERVAL}s, " | |
| f"start delay {START_DELAY}s" | |
| ) | |
| if START_DELAY and not _sleep(START_DELAY): | |
| return 0 | |
| current = _lines() | |
| last = _load_last_trained(current) | |
| if last > current: | |
| last = current | |
| _save_state(last) | |
| elif not STATE.exists() and last == current: | |
| _save_state(last) | |
| _say(f"persistent baseline: corpus={current}, last_trained={last}") | |
| while not _stopping(): | |
| current = _lines() | |
| new_lines = current - last | |
| if new_lines >= MIN_NEW: | |
| if _mem_too_high(): | |
| _say( | |
| f"corpus {current} (+{new_lines}) - RAM guard active; " | |
| "training deferred" | |
| ) | |
| else: | |
| before = CHECKPOINT.stat().st_mtime_ns if CHECKPOINT.is_file() else 0 | |
| _say(f"corpus {current} (+{new_lines}) - bounded training burst") | |
| code, output = _run_burst() | |
| tail = "\n".join(output.strip().splitlines()[-8:]) | |
| if tail: | |
| _say("trainer tail:\n" + tail) | |
| after = CHECKPOINT.stat().st_mtime_ns if CHECKPOINT.is_file() else 0 | |
| if code == 0 and after != before: | |
| last = current | |
| _save_state(last) | |
| _say(f"checkpoint advanced; durable baseline={last}") | |
| elif code is None: | |
| _say("stop requested; active trainer terminated cleanly") | |
| break | |
| else: | |
| _say( | |
| f"burst did not advance checkpoint (return={code}); " | |
| "new lines remain due for retry" | |
| ) | |
| else: | |
| _say(f"corpus {current} (+{new_lines}) - waiting for {MIN_NEW - new_lines} more") | |
| if not _sleep(INTERVAL): | |
| break | |
| _say("stopped with Cosmos; checkpoint and corpus remain persistent") | |
| return 0 | |
| finally: | |
| lock_handle.close() | |
| if __name__ == "__main__": | |
| raise SystemExit(main()) | |