malaiwah/GLM-5.3-Flash-TR3-8bpw

Correct fidelity claims: preserve lane, panel and native-serving limits

Add snapshot-pinned QFS size–KL comparison plot

cards: corrected quantization scope (routed experts + MTP only; attention/dense-MLP were never quantized), excess_over_control rename (P1-05), document-level statistical correction (P1-15), power-arithmetic fix (CC-01). See quant-fidelity-suite docs/PUBLISHED-CORRECTIONS.md

cards: repo paths moved k6/ -> engines/ upstream; fix deep links (were 404)

disclose that materialization-receipt.json names a destroyed filesystem

card: scope disclosure - the published KLD is a panel25 number, and brandonmusic's calibration-clean scope moves it -12.55%

card: fidelity provenance annotation (model-index result + x_fidelity block) — body unchanged

docs: publish live-qualified K8 serving profile

card: parts-bin dataset published (548.5 GB, 223,389 files) — link added

card: BF16 floor removed — quantization-attributable error (K8 2.52x better than K6)

SEALED: 0.012384191 over the full panel, two bitwise-identical cold runs

card: explicit Hub lineage note (two sibling roots), cross-links to the measured family, discovery tags

card: preliminary full-panel K8 result (0.012384, 1.66x better than FP8 at the same size)

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

initial commit