Joseph Magly
b25b3f3b66
fix: harden quantized checkpoint integration
2026-08-16 12:57:17 -04:00
Brian Bell
b6a1727cb6
test+docs: quant_dequant test suite, theory journal engineering log
...
33 CPU-only tests: FP8 block-wise/per-channel round-trips, NVFP4
round-trips (direct + reciprocal scales, native vs manual unpack
agreement), scheme detection incl. ModelOpt MIXED_PRECISION, surgery
guard raises, and tiny synthetic FP8/NVFP4 GPT-2 checkpoints through
load_model end-to-end. Full suite: 870 passed (8 failures pre-exist on
main, verified against pristine checkout).
docs/theory_journal.md Appendices E-E2: engineering log of the 12
findings from implementation and real-checkpoint validation (nibble
order conventions, mixed-precision layouts, the 96GB OOM and the
chunked-unpack fix, transformers 5.x drift shims, Omni wrapper unwrap).
2026-08-16 12:11:12 -04:00
Joseph Magly
42b30f7e5b
docs: record Gate 3 conditional evidence
2026-08-16 09:34:24 -04:00
Joseph Magly
fa233fd8c9
ci: make CUDA conditional lane GPU-capable
2026-08-16 09:23:22 -04:00
Joseph Magly
baf5331730
docs: align conditional claim boundary
2026-08-16 09:12:37 -04:00
Joseph Magly
c90240f1e9
test: govern unavailable conditional environments
2026-08-16 09:05:41 -04:00
Joseph Magly
c1a1275291
ci: add conditional environment test gates
2026-08-14 14:29:14 -04:00
Joseph Magly
e7b658c0c8
ci: add reproducible supply-chain gates
2026-08-14 12:27:15 -04:00
faber and Claude Opus 4.6
04b8ec60cb
Add ASPA framework, AutoObliterator, Watchtower, expanded eval corpus
...
New core modules:
- auto_obliterate.py: Automated multi-iteration obliteration pipeline
- watchtower.py: HF Hub model discovery and tracking
- ui_watchtower.py: Gradio tabs for Watchtower (ready for app.py wiring)
- hard_negative.py: Residue mining from refusal audits
- model_profile.py: Parameter profiling from safetensors/config
- bestiary_sync.py: Sync models from PlinyOS BESTIARY registry
- models_client.py: Lightweight HF model list client
Framework enhancements:
- abliterate.py: ASPA source-tethering, step gradient blending, hard-negative residue support
- cli.py: self-improve command, model profiling, hard-negative flags
- prompts.py: Expanded 842-prompt refusal eval corpus across 10 categories
- __init__.py: New exports (Watchtower, AutoObliterator)
Reference implementations (14 scripts):
- ASPA sweep, gradient search, coherence eval, MMLU benchmarks
- Pareto controller, refusal sniper, stock comparisons
Documentation:
- README: Research framing, responsible use section, comprehensive disclaimer
- docs/beyond_sota_roadmap.md, docs/recursive_self_improvement.md
Tests: 4 new test files (354 lines)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-06-09 03:54:38 -04:00
pliny
69fa63ac43
Add files via upload
2026-03-08 12:07:56 -07:00
pliny
984ce14059
Add files via upload
2026-03-05 10:03:46 -08:00
pliny
66ea4a6f86
Add files via upload
2026-03-05 00:50:44 -08:00
pliny
0f6114fe87
Add files via upload
2026-03-04 12:38:18 -08:00
Joseph Magly