12 GB

Ctrl+K

1 contributor

gemma4_e4b_qat_decode_int4lin: 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

860dfc6 verified about 1 month ago

gemma4_e4b_qat_decode_int4lin
gemma4_e4b_qat_decode_int4lin: 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 about 1 month ago
gemma4_e4b_qat_decode_int4lin_aotc_h18p
Add the chat template and stop at the end of a turn 3 months ago
gemma4_e4b_qat_decode_int4lin_tbl
gemma4_e4b_qat_decode_int4lin_tbl: 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 about 1 month ago