{"slug": "v0-5-0-of-pssa-a-non-transformer-language-model", "title": "V0.5.0 of PSSA: a non-transformer language model", "summary": "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.", "body_md": "## Repository navigation\n\nFirst tagged release, matching the crate version (0.5.0).\n\nHighlights across the project so far:\n\n- 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.\n- 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.\n- 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.\n- 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).\n- 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.\n- 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.", "url": "https://wpnews.pro/news/v0-5-0-of-pssa-a-non-transformer-language-model", "canonical_source": "https://github.com/Sparticle62ops/pssa/releases/tag/v0.5.0", "published_at": "2026-11-01 07:11:12+00:00", "updated_at": "2026-11-01 07:20:09.016646+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "ai-research", "ai-tools", "developer-tools"], "entities": ["PSSA", "Qwen3", "CUDA", "cuBLAS", "WebGPU", "Hugging Face"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/v0-5-0-of-pssa-a-non-transformer-language-model", "markdown": "https://wpnews.pro/news/v0-5-0-of-pssa-a-non-transformer-language-model.md", "text": "https://wpnews.pro/news/v0-5-0-of-pssa-a-non-transformer-language-model.txt", "jsonld": "https://wpnews.pro/news/v0-5-0-of-pssa-a-non-transformer-language-model.jsonld"}}