auto ckpt ckpt_400k.pt

auto ckpt ckpt_400k.pt

auto ckpt ckpt_240k.pt

auto ckpt ckpt_380k.pt

auto ckpt ckpt_380k.pt

auto ckpt ckpt_360k.pt

auto ckpt ckpt_360k.pt

auto ckpt ckpt_340k.pt

auto ckpt ckpt_340k.pt

auto ckpt ckpt_200k.pt

auto ckpt ckpt_400k.pt

auto ckpt ckpt_400k.pt

fix: loader dopasowywał fenomeny po podciągu (6 fenomenów ×2, 73000 zamiast 67000); dokładne dopasowanie + asercja 67000

auto ckpt ckpt_380k.pt

RB4 runda 3: blend_rb4/extract/launch_r3 + build_v2_blend fix (eot z tokenizera, brak klucza synth = stop); skan egress GREEN

auto ckpt ckpt_380k.pt

auto ckpt ckpt_360k.pt

auto ckpt ckpt_360k.pt

Upload eval_push.py with huggingface_hub

auto ckpt ckpt_160k.pt

auto ckpt ckpt_340k.pt

Upload eval_push.py with huggingface_hub

auto ckpt ckpt_340k.pt

decontam-verify kept sample for Hart

Upload dump_kept_sample.py with huggingface_hub

Upload pod_prep.sh with huggingface_hub

remove mislabeled ckpt (was step-320000, autopush-race); canonical=ckpt_320k

remove mislabeled ckpt (was step-320000, autopush-race); canonical=ckpt_320k

remove mislabeled ckpt (was step-320000, autopush-race); canonical=ckpt_320k

remove mislabeled ckpt (was step-320000, autopush-race); canonical=ckpt_320k

Upload ckpt_autopush.py with huggingface_hub

Upload pod_prep.sh with huggingface_hub

Upload fabryka_push.py with huggingface_hub

Upload ckpt_autopush.py with huggingface_hub

Upload fork_launch.sh with huggingface_hub

Upload blend_edu.py with huggingface_hub

Upload build_decontam_index.py with huggingface_hub

Upload build_v2_blend.py with huggingface_hub

auto ckpt 120000

auto ckpt 80000

Upload v2b/ckpt_40k.pt with huggingface_hub

auto ckpt 80000

card: honest wiki correction (byte_ppl 2.372 / BPB 1.246 / eff ~75.9); maintainer re-benchmark PR#78; ARC-Easy 47.94 exact-match

auto ckpt 40000

card: dedup 64M load-recipe (single clean block)

glint_parity_eval: arch-aware loader (Qwen3 cfg from ckpt) - fix 64M maintainer load

card: add 64M Qwen3 load-recipe (maintainer audit load-safety)

Upload glint_parity_eval.py with huggingface_hub

auto ckpt 160000

card: 64M #6 flagship, board-protocol verified (glint bare-prompt: eff 77.51 / ARC 47.94)