Skip to content
#

calibrated-models

Star

Here is 1 public repository matching this topic...

SpellingDragon / system-one-study

Star 0

System-One: a calibrated on-device System-1 decision engine (from scratch). TileLang kernels for Ascend 910B & Apple MPS, SFT -> on-policy distillation -> RLCD training stack, OpenSpec multi-level change management. Two-track course reference.

reinforcement-learning reproducible-research multi-agent course-project lora mps knowledge-distillation model-evaluation decision-engine apple-silicon ascend-npu qwen spec-driven-development openspec on-policy-distillation system-1 rlcd tilelang calibrated-models
  • Updated Oct 25, 2026
  • Python

Add this topic to your repo

To associate your repository with the calibrated-models topic, visit your repo's landing page and select "manage topics."

Learn more