CoolFace
Modelpublic

mlboydaisuke/Gemma-4-12B-CoreAI

sourceHugging Faceapache-2.0updated 9d agoView on Hugging Face
1likes964downloads
26 commits on main
ad0342a9d ago

Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated)

mlboydaisuke
a7bfe1b9d ago

gemma4_12b_qat_decode_int4linsym_msdpa_g8: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py

mlboydaisuke
266c0459d ago

gemma4_12b_qat_decode_int8lin_msdpa_g8: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py

mlboydaisuke
de76f9d16d ago

gen-cards: regenerate Use-it block

mlboydaisuke
7026efd16d ago

Card: DeviceMark row (2026-09)

mlboydaisuke
a9c431f18d ago

Card: definition line (Core AI, 2026-09)

mlboydaisuke
a2a035519d ago

Match the License section to the base card (Apache License 2.0)

mlboydaisuke
899d3a219d ago

Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes)

mlboydaisuke
66651a719d ago

Card: license metadata now matches the base model card (apache-2.0 + Gemma 4 license link)

mlboydaisuke
bb5982529d ago

gen-cards: regenerate Use-it block

mlboydaisuke
6f360ad1mo ago

Link the card back to its collection and the request box

mlboydaisuke
f478a131mo ago

Add config.json so the Hub can count downloads

mlboydaisuke
215cd932mo ago

Take Google's 2026-07-09 canonical chat template

mlboydaisuke
a9672e32mo ago

gen-cards: regenerate Use-it block

mlboydaisuke
feff92c3mo ago

gen-cards: regenerate Use-it block

mlboydaisuke
ac2ca703mo ago

gen-cards: add Use-it markers

mlboydaisuke
5623d643mo ago

chat-EOS fix: eos_token -> <turn|> (clean stop in generic apps)

mlboydaisuke
2c38bf93mo ago

chat-EOS fix: eos_token -> <turn|> (clean stop in generic apps)

mlboydaisuke
d619e323mo ago

Gemma 4 12B: drop simple-kernel gemma4_12b_qat_decode_int8lin_msdpa (superseded by _g8)

mlboydaisuke
34ccf9a3mo ago

Gemma 4 12B: gemma4_12b_qat_decode_int4linsym_msdpa_g8 (higher-occupancy decode bundle)

mlboydaisuke
d1f03bb3mo ago

Gemma 4 12B: gemma4_12b_qat_decode_int8lin_msdpa_g8 (higher-occupancy decode bundle)

mlboydaisuke
24ded103mo ago

Gemma 4 12B: card -> higher-occupancy (_g8) kernel as the ship

mlboydaisuke
99f1dbb3mo ago

Gemma 4 12B: gemma4_12b_qat_decode_int8lin_msdpa (metal-sdpa decode bundle)

mlboydaisuke
74dec653mo ago

Gemma 4 12B: Gemma Terms of Use

mlboydaisuke
2e6e8ab3mo ago

Gemma 4 12B: model card

mlboydaisuke
0aec5483mo ago

initial commit

mlboydaisuke