34.3 GB

Ctrl+K

1 contributor

History: 79 commits

mlboydaisuke

gen-cards: regenerate Use-it block

6f834f1 verified about 9 hours ago

gpu-pipelined-b2
Add the chat template and stop at the end of a turn 2 months ago
gpu-pipelined
gemma4_e2b_qat_vl_vision.aimodel: 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 11 days ago
ios-ane
gemma4_e2b_hostcache_chunk6_int8.aimodel: 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 11 days ago
ios-frontend
E2B QAT gather tables (checkpoint-derived - pair with the QAT bundles) 4 months ago
ios-gpu
gemma4_e2b_metal_int4km_L35.aimodel: 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 11 days ago
macos
gemma4_e2b_metal_int8v3_L35.aimodel: 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 11 days ago
.gitattributes

6.95 kB
Add b2 (beta3-loadable) bundle under gpu-pipelined-b2/gemma4_e2b_qat_decode_int4lin_tbl_aotc_h18p/ (b1 retained) 2 months ago
README.md

18.8 kB
gen-cards: regenerate Use-it block about 9 hours ago
config.json

306 Bytes
Add root config.json (Hub download-stats query file + framework pointer) 4 months ago