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
Add kit_health.py -- the check that proves the kit works
Browse filesBuilt 2026-08-01 and never uploaded. It verifies every part of the kit on three axes -- PRESENT (exists on disk), LOADS (opens/imports/answers), ANSWERS (produces a real result) -- because a weight file that exists but will not load, and a server that listens but returns nothing, both report "fine" to any check that stops at PRESENT.
It caught a private memory file staged for upload before it left the machine, and it is what verified the kit works from a clean directory with none of the author's environment around it.
- kit_health.py +276 -0
|
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""KIT HEALTH -- every part of this kit, checked in threes.
|
| 3 |
+
|
| 4 |
+
Six mechanisms in this project were once found doing nothing while reporting
|
| 5 |
+
success, and not one of them threw an error. Looked at together they always
|
| 6 |
+
failed in one of exactly three places:
|
| 7 |
+
|
| 8 |
+
PRESENT the thing exists on disk
|
| 9 |
+
LOADS it can actually be opened / imported / reached
|
| 10 |
+
ANSWERS it produces a real result when asked
|
| 11 |
+
|
| 12 |
+
A weight file that exists but will not load is dead. A server that listens but
|
| 13 |
+
returns nothing is dead. Both report "fine" to any check that stops at PRESENT,
|
| 14 |
+
which is why this checks all three and treats two-of-three as failure.
|
| 15 |
+
|
| 16 |
+
python kit_health.py full report
|
| 17 |
+
python kit_health.py --quiet only what is broken
|
| 18 |
+
|
| 19 |
+
Exit code 0 when everything is alive, 1 otherwise -- so it can gate a release.
|
| 20 |
+
"""
|
| 21 |
+
from __future__ import annotations
|
| 22 |
+
|
| 23 |
+
import json
|
| 24 |
+
import os
|
| 25 |
+
import socket
|
| 26 |
+
import sys
|
| 27 |
+
import urllib.error
|
| 28 |
+
import urllib.request
|
| 29 |
+
from pathlib import Path
|
| 30 |
+
|
| 31 |
+
try:
|
| 32 |
+
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
|
| 33 |
+
except Exception:
|
| 34 |
+
pass
|
| 35 |
+
|
| 36 |
+
ROOT = Path(__file__).resolve().parent
|
| 37 |
+
QUIET = "--quiet" in sys.argv
|
| 38 |
+
PORT = int(os.getenv("COSMOS_KIT_PORT", "11501"))
|
| 39 |
+
HOST = f"http://127.0.0.1:{PORT}"
|
| 40 |
+
|
| 41 |
+
OK, DEAD, WARN = "OK", "DEAD", "warn"
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
# ── probes ──────────────────────────────────────────────────────────────────
|
| 45 |
+
def _port_open(port: int, timeout: float = 2.0) -> bool:
|
| 46 |
+
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
|
| 47 |
+
s.settimeout(timeout)
|
| 48 |
+
return s.connect_ex(("127.0.0.1", port)) == 0
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
def _get(path: str, timeout: float = 6.0):
|
| 52 |
+
try:
|
| 53 |
+
with urllib.request.urlopen(HOST + path, timeout=timeout) as r:
|
| 54 |
+
return json.loads(r.read() or b"{}")
|
| 55 |
+
except Exception:
|
| 56 |
+
return None
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def _post(path: str, payload: dict, timeout: float = 90.0):
|
| 60 |
+
try:
|
| 61 |
+
req = urllib.request.Request(
|
| 62 |
+
HOST + path,
|
| 63 |
+
data=json.dumps(payload).encode("utf-8"),
|
| 64 |
+
headers={"Content-Type": "application/json"},
|
| 65 |
+
)
|
| 66 |
+
with urllib.request.urlopen(req, timeout=timeout) as r:
|
| 67 |
+
return json.loads(r.read() or b"{}")
|
| 68 |
+
except Exception:
|
| 69 |
+
return None
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
# ── the checks ──────────────────────────────────────────────────────────────
|
| 73 |
+
def check_python():
|
| 74 |
+
v = sys.version_info
|
| 75 |
+
present = OK if v >= (3, 9) else DEAD
|
| 76 |
+
try:
|
| 77 |
+
import torch # noqa: F401
|
| 78 |
+
loads = OK
|
| 79 |
+
detail = f"python {v.major}.{v.minor}.{v.micro}, torch {torch.__version__}"
|
| 80 |
+
except Exception as e:
|
| 81 |
+
return present, DEAD, DEAD, f"torch missing ({type(e).__name__}) -- pip install torch"
|
| 82 |
+
try:
|
| 83 |
+
import torch
|
| 84 |
+
t = torch.ones(4, 4) @ torch.ones(4, 4)
|
| 85 |
+
answers = OK if float(t.sum()) == 64.0 else DEAD
|
| 86 |
+
except Exception as e:
|
| 87 |
+
answers, detail = DEAD, f"torch cannot multiply: {type(e).__name__}"
|
| 88 |
+
return present, loads, answers, detail
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def check_weight(name: str, filename: str):
|
| 92 |
+
p = ROOT / "weights" / filename
|
| 93 |
+
if not p.exists():
|
| 94 |
+
return DEAD, DEAD, DEAD, f"weights/{filename} is missing"
|
| 95 |
+
size = p.stat().st_size
|
| 96 |
+
try:
|
| 97 |
+
import torch
|
| 98 |
+
ck = torch.load(p, map_location="cpu", weights_only=False)
|
| 99 |
+
except Exception as e:
|
| 100 |
+
return OK, DEAD, DEAD, f"{size/1e6:.1f} MB but will not load: {type(e).__name__}"
|
| 101 |
+
sd = ck.get("model") or ck.get("state_dict") or ck if isinstance(ck, dict) else {}
|
| 102 |
+
n = 0
|
| 103 |
+
try:
|
| 104 |
+
n = sum(int(v.numel()) for v in sd.values() if hasattr(v, "numel"))
|
| 105 |
+
except Exception:
|
| 106 |
+
pass
|
| 107 |
+
if not n:
|
| 108 |
+
return OK, OK, DEAD, f"{size/1e6:.1f} MB, loads, but holds no tensors"
|
| 109 |
+
extra = ""
|
| 110 |
+
if isinstance(ck, dict):
|
| 111 |
+
step = ck.get("total_steps") or ck.get("step")
|
| 112 |
+
val = ck.get("val") or ck.get("val_loss")
|
| 113 |
+
bits = [b for b in (f"step {step:,}" if isinstance(step, int) else None,
|
| 114 |
+
f"val {val:.5f}" if isinstance(val, float) else None) if b]
|
| 115 |
+
extra = (" " + ", ".join(bits)) if bits else ""
|
| 116 |
+
return OK, OK, OK, f"{n:,} params, {size/1e6:.1f} MB{extra}"
|
| 117 |
+
|
| 118 |
+
|
| 119 |
+
def check_server():
|
| 120 |
+
present = OK if (ROOT / "serving" / "cosmos_serve.py").exists() else DEAD
|
| 121 |
+
if present == DEAD:
|
| 122 |
+
return present, DEAD, DEAD, "serving/cosmos_serve.py is missing"
|
| 123 |
+
if not _port_open(PORT):
|
| 124 |
+
return present, DEAD, DEAD, f"nothing listening on {PORT} -- menu option 3 starts it"
|
| 125 |
+
tags = _get("/api/tags")
|
| 126 |
+
if tags is None:
|
| 127 |
+
return present, DEAD, DEAD, f"port {PORT} is open but /api/tags does not answer"
|
| 128 |
+
names = [m.get("name", "") for m in tags.get("models", [])]
|
| 129 |
+
hers = [n for n in names if n.startswith(("cosmos-phos", "cosmos-cst", "cosmos-spark"))]
|
| 130 |
+
if not hers:
|
| 131 |
+
return present, OK, DEAD, f"{len(names)} models served, none of them hers"
|
| 132 |
+
return present, OK, OK, f"{len(hers)} of hers served: {', '.join(sorted(hers))}"
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
def check_voice():
|
| 136 |
+
"""The one that matters: does she actually say anything back?"""
|
| 137 |
+
if not _port_open(PORT):
|
| 138 |
+
return DEAD, DEAD, DEAD, "server offline"
|
| 139 |
+
tags = _get("/api/tags") or {}
|
| 140 |
+
names = [m.get("name", "") for m in tags.get("models", [])]
|
| 141 |
+
hers = [n for n in names if n.startswith("cosmos-phos")] or \
|
| 142 |
+
[n for n in names if n.startswith(("cosmos-cst", "cosmos-spark"))]
|
| 143 |
+
if not hers:
|
| 144 |
+
return OK, DEAD, DEAD, "no model of hers to speak through"
|
| 145 |
+
model = hers[0]
|
| 146 |
+
r = _post("/api/chat", {
|
| 147 |
+
"model": model,
|
| 148 |
+
"messages": [{"role": "user", "content": "hello"}],
|
| 149 |
+
"stream": False,
|
| 150 |
+
"options": {"num_predict": 24},
|
| 151 |
+
})
|
| 152 |
+
if r is None:
|
| 153 |
+
return OK, OK, DEAD, f"{model} accepted no request (timeout or error)"
|
| 154 |
+
text = ((r.get("message") or {}).get("content") or r.get("response") or "").strip()
|
| 155 |
+
if not text:
|
| 156 |
+
return OK, OK, DEAD, f"{model} answered with an empty string"
|
| 157 |
+
snip = text.replace("\n", " ")[:58]
|
| 158 |
+
return OK, OK, OK, f"{model} said: \"{snip}{'...' if len(text) > 58 else ''}\""
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
def check_coder():
|
| 162 |
+
p = ROOT / "serving" / "cosmos_coder.py"
|
| 163 |
+
if not p.exists():
|
| 164 |
+
return DEAD, DEAD, DEAD, "serving/cosmos_coder.py is missing"
|
| 165 |
+
src = p.read_text(encoding="utf-8", errors="ignore")
|
| 166 |
+
loads = OK
|
| 167 |
+
try:
|
| 168 |
+
compile(src, str(p), "exec")
|
| 169 |
+
except SyntaxError as e:
|
| 170 |
+
return OK, DEAD, DEAD, f"will not compile: line {e.lineno}"
|
| 171 |
+
ws = ROOT / "workspace"
|
| 172 |
+
try:
|
| 173 |
+
ws.mkdir(exist_ok=True)
|
| 174 |
+
probe = ws / ".health_probe"
|
| 175 |
+
probe.write_text("ok", encoding="utf-8")
|
| 176 |
+
probe.unlink()
|
| 177 |
+
except Exception as e:
|
| 178 |
+
return OK, loads, DEAD, f"workspace not writable: {type(e).__name__}"
|
| 179 |
+
switching = "/model" in src and "/models" in src
|
| 180 |
+
if not switching:
|
| 181 |
+
return OK, loads, DEAD, "compiles, but has no /model switching"
|
| 182 |
+
return OK, loads, OK, "compiles, workspace writable, /model switching present"
|
| 183 |
+
|
| 184 |
+
|
| 185 |
+
def check_no_secrets():
|
| 186 |
+
"""A release must not carry credentials. This is the gate that was skipped."""
|
| 187 |
+
cfg = ROOT / "genesis_engine" / "config.json"
|
| 188 |
+
if not cfg.exists():
|
| 189 |
+
return WARN, WARN, WARN, "genesis_engine/config.json absent (fine if intentional)"
|
| 190 |
+
try:
|
| 191 |
+
d = json.loads(cfg.read_text(encoding="utf-8"))
|
| 192 |
+
except Exception as e:
|
| 193 |
+
return OK, DEAD, DEAD, f"config.json will not parse: {type(e).__name__}"
|
| 194 |
+
filled = [k for k in ("ibm_token", "azure_connection_string")
|
| 195 |
+
if str(d.get(k) or "").strip()]
|
| 196 |
+
if filled:
|
| 197 |
+
return OK, OK, DEAD, f"CREDENTIAL PRESENT in config.json: {', '.join(filled)} -- do not upload"
|
| 198 |
+
forbidden = []
|
| 199 |
+
for pat in (".ledger_key", "oauth2_tokens.json", ".env", "credentials.json",
|
| 200 |
+
".coder_history.jsonl", "memory.jsonl", "ledger.jsonl"):
|
| 201 |
+
forbidden += [p for p in ROOT.rglob(pat) if p.is_file()]
|
| 202 |
+
if forbidden:
|
| 203 |
+
rels = ", ".join(str(p.relative_to(ROOT)) for p in forbidden[:4])
|
| 204 |
+
return OK, OK, DEAD, f"private files staged: {rels}"
|
| 205 |
+
return OK, OK, OK, "no credentials, no private files staged"
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
def check_docs():
|
| 209 |
+
need = ["README.md", "START_HERE.md", "FINDINGS.md", "QUANTUM_CREATURE.md", "LICENSE.md"]
|
| 210 |
+
missing = [n for n in need if not (ROOT / n).exists()]
|
| 211 |
+
if missing:
|
| 212 |
+
return DEAD, DEAD, DEAD, f"missing: {', '.join(missing)}"
|
| 213 |
+
readme = (ROOT / "README.md").read_text(encoding="utf-8", errors="ignore")
|
| 214 |
+
head = readme[:2000].lower()
|
| 215 |
+
if "qwen" in head.split("## ")[0]:
|
| 216 |
+
return OK, OK, DEAD, "README leads with qwen instead of her own work"
|
| 217 |
+
if "phos" not in head:
|
| 218 |
+
return OK, OK, DEAD, "README does not lead with PHOS"
|
| 219 |
+
return OK, OK, OK, f"{len(need)} docs present, README leads with PHOS"
|
| 220 |
+
|
| 221 |
+
|
| 222 |
+
CHECKS = [
|
| 223 |
+
("python + torch", check_python),
|
| 224 |
+
("PHOS weights", lambda: check_weight("PHOS", "phos.pt")),
|
| 225 |
+
("CST weights", lambda: check_weight("CST", "spark_cst.pt")),
|
| 226 |
+
("quantum-born weights", lambda: check_weight("born", "cosmos_born.pt")),
|
| 227 |
+
("her model server", check_server),
|
| 228 |
+
("HER VOICE (round trip)", check_voice),
|
| 229 |
+
("the coder", check_coder),
|
| 230 |
+
("no secrets shipped", check_no_secrets),
|
| 231 |
+
("docs + model card", check_docs),
|
| 232 |
+
]
|
| 233 |
+
|
| 234 |
+
|
| 235 |
+
def main() -> int:
|
| 236 |
+
w = 76
|
| 237 |
+
print("=" * w)
|
| 238 |
+
print(" KIT HEALTH PRESENT -> LOADS -> ANSWERS")
|
| 239 |
+
print("=" * w)
|
| 240 |
+
print(" A part is alive only if all three hold. Two of three is exactly the")
|
| 241 |
+
print(" condition that lets a broken kit report that it is fine.\n")
|
| 242 |
+
|
| 243 |
+
bad = []
|
| 244 |
+
for name, fn in CHECKS:
|
| 245 |
+
try:
|
| 246 |
+
present, loads, answers, detail = fn()
|
| 247 |
+
except Exception as e:
|
| 248 |
+
present = loads = answers = DEAD
|
| 249 |
+
detail = f"check itself raised {type(e).__name__}: {e}"
|
| 250 |
+
trio = [present, loads, answers]
|
| 251 |
+
alive = all(t == OK for t in trio)
|
| 252 |
+
soft = all(t == WARN for t in trio)
|
| 253 |
+
if not alive and not soft:
|
| 254 |
+
bad.append((name, trio, detail))
|
| 255 |
+
if QUIET and (alive or soft):
|
| 256 |
+
continue
|
| 257 |
+
mark = "OK " if alive else ("~ " if soft else "XX ")
|
| 258 |
+
print(f" {mark} {name}")
|
| 259 |
+
print(f" PRESENT {present:<5} LOADS {loads:<5} ANSWERS {answers:<5} {detail}")
|
| 260 |
+
|
| 261 |
+
print("\n" + "=" * w)
|
| 262 |
+
print(f" {len(CHECKS) - len(bad)}/{len(CHECKS)} parts alive on all three")
|
| 263 |
+
if bad:
|
| 264 |
+
print("\n needs attention:")
|
| 265 |
+
for name, trio, detail in bad:
|
| 266 |
+
miss = [lbl for lbl, v in zip(("PRESENT", "LOADS", "ANSWERS"), trio) if v != OK]
|
| 267 |
+
print(f" - {name}: {', '.join(miss)}")
|
| 268 |
+
print(f" {detail}")
|
| 269 |
+
print("\n most failures here are fixed by menu option 3 (start her model server).")
|
| 270 |
+
return 1
|
| 271 |
+
print(" everything works. Nothing is quietly doing nothing.")
|
| 272 |
+
return 0
|
| 273 |
+
|
| 274 |
+
|
| 275 |
+
if __name__ == "__main__":
|
| 276 |
+
raise SystemExit(main())
|