Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
fix(cli): convert needs its own guard — --model is its destination
Mario Gutiérrezd93be65e45ad
diff --git a/c/coli b/c/coliindex 623b75b6..2b4b457d 100755--- a/c/coli+++ b/c/coli@@ -1034,6 +1034,11 @@ def cmd_bench(a):def cmd_convert(a):banner("convert")+ # here --model is the DESTINATION the converted weights are written to, not an+ # existing snapshot, so it needs its own wording rather than need_model's.+ if not a.model:+ sys.exit(f"{C.yel}no output directory given.{C.r}\n"+ f" --model <dir> is where the converted model is written")# python con torch/safetensors: l'ambiente del progetto se c'e', altrimenti quello correntevenv_py = os.path.join(HERE, "mio_env", "Scripts" if sys.platform == "win32" else "bin", "python3")py = venv_py if os.path.exists(venv_py) else sys.executable