Hugging Face's logo

infosave
/
Nanbeige4.2-3Bcmf

Text Generation
cortiq
cmf
nanbeige
looped-transformer
reasoning
quantized
Model card Files
xet
 Community
Nanbeige4.2-3Bcmf / experiments

Commit History

  1. gfx skill FINAL: masked runtime gate -5.1% vs backbone (3.974/4.187), replica 3.923; trained masters in q8_row; apply: cortiq skill apply nanbeige42-3b-q4t.cmf nanbeige42-gfx.skill.cmf -o gfx.cmf

    infosave
    Verified signature
    08f9d91

  2. coding skill FINAL: masked runtime gate -1.1% vs backbone (9.633/9.743); trained masters in q8_row; apply: cortiq skill apply nanbeige42-3b-q4t.cmf nanbeige42-code.skill.cmf -o code.cmf

    infosave
    Verified signature
    a95e562

  3. coding skill (557 MB delta): masked replica -2.2% vs backbone (9.529/9.746), bare runtime gate +7.7% (mask not yet applied on quantized storage); phase A bottom uncaptured at 150 steps - a longer A will deepen it. apply: cortiq skill apply nanbeige42-3b-q4t.cmf nanbeige42-code.skill.cmf -o code.cmf

    infosave
    Verified signature
    00a98ea

  4. gfx specialist v2: strict-f32 phase A, bottom 4.225@4.4%, gate -1.5% vs backbone

    infosave
    Verified signature
    7df9a8a

  5. standalone gfx skill (557 MB delta): cortiq skill apply nanbeige42-3b-q4t.cmf nanbeige42-gfx.skill.cmf -o specialist.cmf

    infosave
    Verified signature
    71ab66a

  1. Upload experiments/nanbeige42-gfx-pervisit-skill.cmf with huggingface_hub

    infosave
    Verified signature
    18d2240

  2. Upload experiments/nanbeige42-gfx-pervisit-skill.cmf with huggingface_hub

    infosave
    Verified signature
    330f5e5