Model card: correct the recalibration — leaderboard is best-fit only, so the like-for-like gap is +0.019; both checkpoints now measured under both packings

Model card: recalibrate val bpb under upstream packing; document the token_bytes regeneration

Model card: step 5568 is now a ready-made nanochat checkpoint (+8-rank optimizer shards)

Flag that val bpb is not comparable across the batched/varlen pipelines

Converter now emits nanochat optimizer shards for an SFT warm-start

Correct optimizer-state notes: SFT needs only the weights; W_O axis is a no-op at d24

Add model card, meta.json, logs, tokenizer, training source, and nanochat converter