Upload run_16m_arcmix/ckpt.pt with huggingface_hub

Upload README.md with huggingface_hub

Upload train_tokenizer.py with huggingface_hub

Upload README.md with huggingface_hub

Upload progress_v5.png with huggingface_hub

Remove abandoned KARD-synthetic pipeline (pivoted to real-data ARC-curation)

Delete charts/scaling_v5_latarnik.png with huggingface_hub

Upload make_progress_chart.py with huggingface_hub

Upload progress_v5.png with huggingface_hub

Upload charts/scaling_v5_latarnik.png with huggingface_hub

Upload glint_16m_expanded_results.json with huggingface_hub

Upload run_16m_expanded/ckpt.pt with huggingface_hub

Upload kard/kard_decontam_semantic.py with huggingface_hub

Upload kard/topics.txt with huggingface_hub

Upload kard/kard_decontam.py with huggingface_hub

Upload kard/kard_generate.py with huggingface_hub

Upload make_board_overlay.py with huggingface_hub

Upload board_overlay_v5.png with huggingface_hub

Upload scaling_v5.png with huggingface_hub

Usage: reference in-repo train_gpt_ref.py and glint_parity_eval.py

Upload glint_parity_eval.py with huggingface_hub

Upload train_gpt_ref.py with huggingface_hub

Polished professional card: model-details, usage, evaluation-protocol, key-findings, roadmap, limitations

Add Usage section (merge best-of-both cards)

Proper English model card: Glint-protocol metrics, honest positioning, corrected corpus/positions

Upload README.md with huggingface_hub

Upload bpe32m_baseline/ckpt.pt with huggingface_hub

Upload README.md with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload bpe16m_10B/ckpt.pt with huggingface_hub

Upload bpe16m_6B/ckpt.pt with huggingface_hub

Upload bpe16m_3.2B/ckpt.pt with huggingface_hub

initial commit