V0.5.0 of PSSA: a non-transformer language model

The PSSA project published its first tagged release, version 0.5.0, matching the crate version, covering a non-transformer language model built around shared-weight Ouro looping and stacked-depth training. The release adds native CUDA/cuBLAS and WebGPU backends with resident weight matrices and packed kernel dispatch for the SSM and memory stages, plus a Qwen3-to-PSSA converter with a pure-Rust teacher forward and a CE + temperature-KL loss verified by finite-difference tests. The TUI was simplified to five category menus replacing a 27-tab strip, with 519 tests green at that merge.

Repository navigation First tagged release, matching the crate version 0.5.0 . Highlights across the project so far: - Training core: parameter-matched transformer baseline, shared-weight Ouro looping, stacked-depth training, batched independent-sequence lanes, resumable learning-rate horizons, gradient clipping and episodic memory value caps, resumable memory growth. - GPU backends: native CUDA/cuBLAS alongside WebGPU, resident weight matrices, packed kernel dispatch for the SSM and memory stages, parity and timing checks, and refusal to run training on software adapters. - Qwen distillation: Qwen3-to-PSSA converter and checkpoint emit, a pure-Rust teacher forward, CE + temperature-KL loss verified by finite-difference tests, per-phase timing breakdowns, and unembedding calibration. - TUI: full restyle braille charts, retro panels through the phase 4 through 12c feature set, then a simplification round: one key grammar, five category menus replacing the 27-tab strip, plain-language help and status lines 519 tests green at that merge . - Docs and site: README rebuilt around measured results and split into focused guides contributing, donate, model math, Qwen distillation math , new logo, FUNDING.yml, Hugging Face checkpoint pointers. - Reliability: hardened CLI parsing and remote input bounds, divergent-loss halt before checkpoint save, honest TUI telemetry panels, Windows platform fixes, and guarded dream replay.