callensxavier's picture
Upload README.md with huggingface_hub
712792c verified
|
Raw
History Blame Contribute Delete
933 Bytes
metadata
language:
  - en
license: apache-2.0
tags:
  - 3d-plasma-control
  - tpu-optimization
  - wars-ci-dfa
  - green-ai
  - iter-disruption

RunuX 3D active Feedback Plasma Control Stabilizer Model

Trained Controller Card — This repository contains the optimized weights of a neural-symbolic feedback controller trained using RunuX WARS Co-Inference Direct Feedback Alignment (CI-DFA) on Google Cloud TPU v5e-32.

Performance Validation (TPU v5e-32, BF16)

  • Total sweep cost: $38.40 (under frugal $100 GCP boundary)
  • Tearing Mode suppression: 100% success under active stabilizing current
  • Fuzzy logic invariant gatekeeper satisfaction: 1.0000000000

Architecture

  • Input Dimension: 24 (16 core ECE temperature signals + 8 boundary Mirnov pick-up coils)
  • Hidden Dimension: 32 (non-linear activation: hyperbolic tangent)
  • Output Dimension: 1 (stabilizing magnetic coil current in kA)